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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15024
    Prev
    Next
    INDEX
    Explanations

    assertion failure

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

    The neuron fires on open‐class, content‐bearing words (especially nouns and verbs) rather than on 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_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
     ouvido
    0.82
    못
    0.82
     сможет
    0.79
     станет
    0.78
    على
    0.77
     afin
    0.77
     ninguém
    0.76
    晔
    0.76
    dı
    0.75
     primeiro
    0.74
    POSITIVE LOGITS
    ્ઞ
    0.78
     Seriously
    0.78
     folgt
    0.75
     Motorsports
    0.73
    ൂ
    0.73
     Substituting
    0.72
    ട്ടുള്ള
    0.72
     モ
    0.71
     Unless
    0.70
     Mixing
    0.70
    Activations Density 0.000%

    No Known Activations