© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    customer facing staff

    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
     incluso
    -1.45
     même
    -1.38
     даже
    -1.36
     sogar
    -1.34
     bahkan
    -1.29
     nawet
    -1.24
    Weg
    -1.19
     dokonce
    -1.16
    爆发
    -1.15
     Develop
    -1.14
    POSITIVE LOGITS
     to
    2.17
     its
    2.13
     that
    1.55
    oacute
    1.36
     tikra
    1.34
    miques
    1.32
    жением
    1.30
     before
    1.28
    breviations
    1.27
    tacles
    1.27
    Activations Density 0.084%

    No Known Activations