Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4034
    Prev
    Next
    INDEX
    Explanations

    the + [noun]

    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
    h
    0.96
     permisos
    0.94
    ક
    0.94
    gments
    0.93
    the
    0.88
     effectués
    0.86
     modalités
    0.86
    timers
    0.84
    footnotes
    0.84
     tercero
    0.84
    POSITIVE LOGITS
     (
    0.80
     possibility
    0.75
     μ
    0.70
     tonic
    0.70
    ̹
    0.70
    сной
    0.69
     \"
    0.68
     Möglichkeit
    0.68
     ¹
    0.68
    рье
    0.68
    Activations Density 0.130%

    No Known Activations