© 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. 14747
    Prev
    Next
    INDEX
    Explanations

    name field

    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
     rezerv
    -1.19
     É
    -1.16
     et
    -1.13
     après
    -1.09
     extraordinaire
    -1.07
    Leider
    -1.03
    Fortnite
    -1.03
    鼇
    -1.02
     управля
    -1.02
     ABSOL
    -1.00
    POSITIVE LOGITS
    there
    1.38
     There
    1.30
     Bourgoin
    1.26
    how
    1.26
     that
    1.23
     why
    1.22
     there
    1.19
     TORONTO
    1.17
     part
    1.17
     Muitos
    1.16
    Activations Density 0.074%

    No Known Activations