© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8056
    Prev
    Next
    INDEX
    Explanations

    the noun after it

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds most strongly to content-bearing words (i.e. higher-salience or topic-specific terms) in a document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "the" when it appears in repetitive, formulaic instructional or technical text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    determinants of noun phrases—especially second-person possessive determiners and definite articles introducing a following noun.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    1.05
    8
    1.05
    6
    1.02
    or
    0.99
    RO
    0.97
    7
    0.97
    4
    0.95
    e
    0.94
    3
    0.94
    1
    0.92
    POSITIVE LOGITS
     minta
    0.81
     уровнем
    0.80
     của
    0.79
    zynarod
    0.77
     esperando
    0.77
     pedir
    0.75
     массы
    0.75
     nível
    0.74
     показатель
    0.74
     ನಾಲ್
    0.73
    Activations Density 0.005%

    No Known Activations