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. 1415
    Prev
    Next
    INDEX
    Explanations

    Control Panel

    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
    عی
    0.95
    rt
    0.95
    gboost
    0.95
    👴
    0.91
    🍮
    0.90
    ल्लभ
    0.88
    처럼
    0.88
    //{
    0.88
    🙆
    0.87
    ✼
    0.87
    POSITIVE LOGITS
    त्व
    0.96
     sabit
    0.95
     peta
    0.90
     iba
    0.88
    ка
    0.88
     paralyzed
    0.86
     Conta
    0.86
     tangga
    0.82
     w
    0.80
     p
    0.79
    Activations Density 0.002%

    No Known Activations