© 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. 39659
    Prev
    Next
    INDEX
    Explanations

    suffer from

    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
     gustado
    -2.66
    廡
    -2.39
    ቍ
    -2.28
    怱
    -2.25
    袿
    -2.23
    觧
    -2.23
    Ꮉ
    -2.19
     miten
    -2.11
    って何
    -2.09
     minera
    -2.09
    POSITIVE LOGITS
    .
    3.73
     
    2.50
    s
    2.34
     to
    2.25
    </h3>
    2.23
    \
    2.20
     A
    2.19
     \
    2.13
     V
    2.11
    на
    2.03
    Activations Density 0.015%

    No Known Activations