© 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. 67801
    Prev
    Next
    INDEX
    Explanations

    smartphone and related technology

    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
    ↵
    -2.86
    2
    -2.64
     REALLY
    -2.44
    1
    -2.34
     VERY
    -2.25
    嫫
    -2.19
     euphoria
    -2.17
     discer
    -2.14
    ()){
    -2.11
     impo
    -2.09
    POSITIVE LOGITS
    k
    2.38
     și
    2.36
    .
    2.31
    ⢓
    2.31
     vertes
    2.27
     और
    2.23
    2.23
     祝福
    2.19
    ;
    2.14
    敝
    2.14
    Activations Density 0.004%
    No Known Activations