© 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. 15257
    Prev
    Next
    INDEX
    Explanations

    Not

    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
    ズム
    0.58
    gitignore
    0.57
    榞
    0.55
    Henry
    0.55
     henry
    0.55
    NewGuid
    0.54
    linebreak
    0.52
    ⟶
    0.52
    ზე
    0.52
    জিৎ
    0.52
    POSITIVE LOGITS
     Specified
    0.73
     defined
    0.73
     specified
    0.73
     défini
    0.68
     graded
    0.67
     définie
    0.66
     given
    0.64
     गिवन
    0.63
     encontrada
    0.63
     Given
    0.62
    Activations Density 0.001%

    No Known Activations