© 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. 59004
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     sorella
    -1.26
    engarkan
    -1.25
    Some
    -1.24
     Several
    -1.24
     Hundreds
    -1.22
     Some
    -1.20
    ettare
    -1.15
     Numerous
    -1.14
     using
    -1.12
    Using
    -1.12
    POSITIVE LOGITS
    ν
    1.48
    皛
    1.43
    憷
    1.39
     personalización
    1.29
     primer
    1.18
    Η
    1.17
    να
    1.16
    øver
    1.16
     apariencia
    1.15
     traducción
    1.14
    Activations Density 0.202%

    No Known Activations