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. 31073
    Prev
    Next
    INDEX
    Explanations

    afraid

    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
    ai
    1.32
    ale
    1.27
    ou
    1.15
    ip
    1.12
    q
    1.09
    ap
    1.07
    L
    1.05
    ished
    1.05
    ero
    1.05
    om
    1.04
    POSITIVE LOGITS
    ের
    1.00
    ه
    0.97
     است
    0.96
    ات
    0.95
    iéndose
    0.93
     Сти
    0.93
     Архиви
    0.92
     المث
    0.92
     للت
    0.91
    هما
    0.90
    Activations Density 0.000%

    No Known Activations