© 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. 7655
    Prev
    Next
    INDEX
    Explanations

    two entities

    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
     nombreuses
    -1.60
    KommentareTeilen
    -1.59
    ruvate
    -1.54
     منذ
    -1.54
    artney
    -1.51
    êque
    -1.45
    翕
    -1.45
    brtc
    -1.43
     viele
    -1.40
    Quién
    -1.40
    POSITIVE LOGITS
     of
    1.90
     carlo
    1.46
     that
    1.39
     leone
    1.32
     taal
    1.31
     industriale
    1.30
     napoli
    1.28
     tenerife
    1.27
     members
    1.26
     fuq
    1.26
    Activations Density 0.015%

    No Known Activations