© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33201
    Prev
    Next
    INDEX
    Explanations

    same or common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     if
    -1.25
     or
    -1.09
     from
    -0.91
     دیگری
    -0.90
     with
    -0.85
     الأخرى
    -0.82
    gerie
    -0.81
    poda
    -0.78
    وانات
    -0.77
     Trying
    -0.76
    POSITIVE LOGITS
    Same
    1.28
     same
    1.23
    同一个
    1.14
     mêmes
    1.10
     shared
    1.10
    identical
    1.09
     réserver
    1.09
     identical
    1.07
     common
    1.06
     dieselbe
    0.99
    Activations Density 0.111%

    No Known Activations