© 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. 15301
    Prev
    Next
    INDEX
    Explanations

    as ever / than ever

    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
    鈊
    -1.52
     znal
    -1.49
     スペシャル
    -1.48
    甪
    -1.47
    sonaro
    -1.46
     zusätz
    -1.46
     légère
    -1.46
     lidé
    -1.46
     ligero
    -1.44
     enju
    -1.44
    POSITIVE LOGITS
    יות
    1.38
     borne
    1.36
    内容
    1.30
    ;
    1.30
    长度
    1.27
    antwortung
    1.27
    している
    1.26
    ptest
    1.21
    ített
    1.21
    kval
    1.20
    Activations Density 0.004%

    No Known Activations