© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34579
    Prev
    Next
    INDEX
    Explanations

    specific tokens and subsequent phrases

    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
    Negative Logits
    a
    1.57
    ه
    1.54
    krieg
    1.53
    ה
    1.50
    al
    1.35
    aun
    1.28
     Neumann
    1.26
     لت
    1.22
    es
    1.19
    सायिक
    1.17
    POSITIVE LOGITS
    ъ
    1.77
    ια
    1.62
    нің
    1.55
    ર
    1.47
    िन
    1.46
    ными
    1.45
     descargar
    1.45
    Excuse
    1.45
    એ
    1.42
    ност
    1.40
    Activations Density 0.001%

    No Known Activations