© 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. 8130
    Prev
    Next
    INDEX
    Explanations

    at some point

    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
     maksi
    -2.25
    鶺
    -2.23
    鐒
    -2.19
    
    -2.16
     plafon
    -2.16
    踯
    -2.13
    ’”
    -2.09
    壜
    -2.05
    ㈮
    -2.03
     alamu
    -2.02
    POSITIVE LOGITS
     of
    2.95
    <em>
    2.56
    in
    2.48
     ''
    2.19
     où
    2.11
    नलोड
    2.11
    f
    2.09
    In
    2.05
     $
    2.03
    However
    1.98
    Activations Density 0.005%

    No Known Activations