© 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. 14525
    Prev
    Next
    INDEX
    Explanations

    be to describe

    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
     
    -2.92
    巨大的
    -2.72
    {
    -2.20
     ehemalige
    -2.17
    独特的
    -2.16
     of
    -2.13
    <bos>
    -2.11
    D
    -2.11
     blaue
    -2.09
     erheben
    -2.03
    POSITIVE LOGITS
     be
    3.53
     to
    3.31
    ፨
    2.53
    鹚
    2.52
    噥
    2.44
    釓
    2.41
     describe
    2.30
    鈰
    2.28
     stockfoto
    2.27
    éton
    2.20
    Activations Density 0.028%

    No Known Activations