© 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. 38993
    Prev
    Next
    INDEX
    Explanations

    museums and halls of fame

    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
    囑
    -1.23
    re
    -1.21
     zwanzig
    -1.20
    alucía
    -1.16
     Betrach
    -1.11
    كما
    -1.09
    也许
    -1.09
    蕺
    -1.09
    ׳
    -1.08
     فقط
    -1.06
    POSITIVE LOGITS
     in
    1.33
     museum
    1.29
     enrique
    1.23
     reiv
    1.23
    кость
    1.20
     what
    1.20
     after
    1.20
     informar
    1.18
     Museum
    1.17
    museum
    1.17
    Activations Density 0.114%

    No Known Activations