© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35017
    Prev
    Next
    INDEX
    Explanations

    actually incorrect

    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
    ج
    1.04
    CONNECTED
    0.93
    ╽
    0.91
    CONTEXT
    0.87
    ╿
    0.87
    ssss
    0.87
    ログイン
    0.87
    ISHING
    0.83
    studentid
    0.83
     आइसलैंड
    0.82
    POSITIVE LOGITS
    ș
    0.95
    et
    0.93
    il
    0.89
    讖
    0.86
    ir
    0.86
     Peki
    0.85
     kommer
    0.85
    t
    0.85
     våra
    0.83
    ar
    0.82
    Activations Density 0.016%

    No Known Activations