© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4063
    Prev
    Next
    INDEX
    Explanations

    architecture and

    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
    ב
    0.70
    گە
    0.68
    тельные
    0.67
    ți
    0.64
    ुप
    0.64
    ва
    0.62
    ực
    0.62
    с
    0.62
     Auc
    0.61
    களில்
    0.61
    POSITIVE LOGITS
    PWM
    0.73
    XRD
    0.71
    ج
    0.70
     playlists
    0.67
    ️⃣
    0.67
    .¹
    0.65
     checklists
    0.64
     thằng
    0.64
     ribonucle
    0.64
     arbej
    0.63
    Activations Density 1.342%

    No Known Activations