© 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. 44799
    Prev
    Next
    INDEX
    Explanations

    article formatting

    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
    isPlaying
    0.84
    ệ
    0.82
     manchas
    0.79
     genética
    0.79
    amı
    0.78
    органи
    0.77
    possibleTypes
    0.77
     termino
    0.77
    TIME
    0.76
    oughby
    0.75
    POSITIVE LOGITS
     Ministers
    0.77
    առ
    0.76
     FPS
    0.75
    ;
    0.75
    去
    0.73
     Biscuit
    0.73
     Geometric
    0.71
    )
    0.71
     Subjects
    0.71
     Business
    0.70
    Activations Density 0.000%

    No Known Activations