© 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. 31-GEMMASCOPE-2-RES-16K
    4. 10603
    Prev
    Next
    INDEX
    Explanations

    along or intermediate stages

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

    The neuron flags semantically rich content words (mainly nouns and verbs) rather than function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     festive
    0.50
     დაი
    0.50
     يوم
    0.49
    跏
    0.48
     الرغم
    0.48
     dawned
    0.47
     пі
    0.47
     Bold
    0.47
    葲
    0.47
    വൃ
    0.46
    POSITIVE LOGITS
     along
    2.92
     Along
    2.92
    Along
    2.92
    along
    2.70
    沿
    2.53
     entlang
    2.23
     вдоль
    1.95
     중간
    1.74
     dọc
    1.74
     langs
    1.70
    Activations Density 0.459%

    No Known Activations