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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14856
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    yla
    0.78
    অ
    0.66
    بھی
    0.63
    <unused60>
    0.62
    உ
    0.60
    quele
    0.59
    अ
    0.57
    </h3>
    0.57
     sprawie
    0.56
    అ
    0.55
    POSITIVE LOGITS
    hesized
    1.21
    ulously
    1.19
    びに
    1.17
    ствий
    1.14
    cially
    1.10
    ifically
    1.09
    imized
    1.08
    perature
    1.06
    duled
    1.06
    uettes
    1.06
    Activations Density 0.538%

    No Known Activations