© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5940
    Prev
    Next
    INDEX
    Explanations

    menu items or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    p
    2.70
    k
    2.20
    m
    2.17
    t
    2.06
    pada
    1.89
    ف
    1.80
    نیا
    1.73
    ن
    1.73
    pura
    1.71
    son
    1.67
    POSITIVE LOGITS
    ோவின்
    2.17
     triglycerides
    2.08
    ור
    2.06
    ñoz
    2.06
    जीलैंड
    2.06
     बदमाशों
    2.06
     PDEs
    2.02
     tassels
    1.98
     Ở
    1.98
    ždy
    1.96
    Activations Density 0.015%

    No Known Activations