© 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. 8197
    Prev
    Next
    INDEX
    Explanations

    directory/code structure

    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
     llevaba
    -1.52
     necesitaba
    -1.45
    ⎜
    -1.24
     vivía
    -1.23
    moveToNext
    -1.18
    putAll
    -1.17
     
    -1.17
     alguna
    -1.17
     necesita
    -1.16
    🏺
    -1.16
    POSITIVE LOGITS
     of
    2.42
    ed
    1.37
    ate
    1.35
    ite
    1.30
     detalló
    1.28
    th
    1.26
     uye
    1.25
    ation
    1.24
     cuit
    1.24
     that
    1.21
    Activations Density 0.022%

    No Known Activations