© 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. 34-GEMMASCOPE-RES-131K
    7. 63324
    Prev
    Next
    INDEX
    Explanations

    javascript code syntax

    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_34/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
    始まる
    -1.24
    始まり
    -1.16
     arreglos
    -1.11
     manicura
    -1.09
     Publicity
    -1.07
    昔の
    -1.07
     tornillos
    -1.06
     клі
    -1.05
     creativos
    -1.05
     シル
    -1.04
    POSITIVE LOGITS
    /
    1.17
    .}(
    1.16
     menina
    1.16
     palha
    1.09
    _
    1.09
    bigint
    1.05
     myös
    1.04
     skola
    1.02
     gramas
    1.02
     europé
    1.02
    Activations Density 0.220%

    No Known Activations