© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14906
    Prev
    Next
    INDEX
    Explanations

    ; accepted after

    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
    他们
    -2.41
     eit
    -2.39
    <bos>
    -2.31
    倓
    -2.27
    LEIA
    -2.25
    媗
    -2.19
     raad
    -2.14
    ౮
    -2.11
    琲
    -2.11
    leſs
    -2.11
    POSITIVE LOGITS
    -\
    2.58
    ).
    2.53
     if
    2.42
    ),
    2.39
    ’
    2.38
    --
    2.34
    ".
    2.34
    [
    2.31
    '),
    2.28
     ;
    2.23
    Activations Density 0.074%

    No Known Activations