© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44469
    Prev
    Next
    INDEX
    Explanations

    toolchain; Cascade Technology

    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
    ان
    1.17
    न
    1.16
    ش
    1.16
    ن
    1.09
    ン
    0.86
    নাত
    0.84
    ки
    0.83
    ہا
    0.81
    ва
    0.81
    ো
    0.79
    POSITIVE LOGITS
    cie
    0.95
    ffi
    0.94
    University
    0.92
     University
    0.90
    arming
    0.88
    riba
    0.88
    ς
    0.86
    📄
    0.86
    tic
    0.86
    rand
    0.84
    Activations Density 0.001%

    No Known Activations