© 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. 10-GEMMASCOPE-RES-131K
    7. 73715
    Prev
    Next
    INDEX
    Explanations

    words starting with Ber

    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_10/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
     they
    -2.45
    嗩
    -2.45
    了很多
    -2.44
     About
    -2.42
    izacji
    -2.42
    噏
    -2.34
    悭
    -2.31
     of
    -2.30
     a
    -2.30
    lusconi
    -2.28
    POSITIVE LOGITS
    \
    2.61
    3
    2.59
    0
    2.52
    鳚
    2.47
    鲻
    2.47
     歳
    2.47
    猡
    2.41
     鋼
    2.33
     給
    2.31
    事實
    2.31
    Activations Density 0.003%

    No Known Activations