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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3012
    Prev
    Next
    INDEX
    Explanations

    clash with a track

    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_16k_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
    O
    1.21
    OM
    1.20
    M
    1.18
    AL
    1.08
    ER
    1.00
     وعند
    1.00
    ي
    1.00
    P
    1.00
    AS
    0.99
    ്ല
    0.99
    POSITIVE LOGITS
     Obituary
    0.95
    ยนต์
    0.95
    お手
    0.94
    ायक
    0.93
    ikke
    0.93
     precisa
    0.92
     τις
    0.91
    iksi
    0.91
     맛있
    0.90
    ق
    0.90
    Activations Density 0.176%

    No Known Activations