© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60791
    Prev
    Next
    INDEX
    Explanations

    insert into

    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
    
    -1.56
     Stanisław
    -1.51
     этого
    -1.42
    ☸
    -1.42
    ított
    -1.41
     sein
    -1.39
    üedad
    -1.38
     wers
    -1.38
     perro
    -1.37
    MANUEL
    -1.36
    POSITIVE LOGITS
     new
    1.87
     As
    1.58
     before
    1.55
    OrUpdate
    1.55
     without
    1.55
     Only
    1.53
     as
    1.48
     Much
    1.48
     into
    1.45
     ONLY
    1.45
    Activations Density 0.014%

    No Known Activations