© 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. 3999
    Prev
    Next
    INDEX
    Explanations

    perspective and perspective shift

    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
    ﺩ
    1.95
     terribly
    1.94
    ت
    1.91
    போதும்
    1.84
    ע
    1.80
    ない
    1.80
    웨어
    1.79
    梆
    1.78
    IO
    1.76
    IFT
    1.76
    POSITIVE LOGITS
    ff
    2.13
    ção
    1.95
     Öffentlichkeit
    1.94
    c
    1.85
    ž
    1.73
     Nähe
    1.63
    bentuk
    1.57
    utiva
    1.57
    ónimo
    1.56
    zza
    1.55
    Activations Density 0.018%

    No Known Activations