© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98471
    Prev
    Next
    INDEX
    Explanations

    J.J. or names with initials

    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_34/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
     утеп
    -0.79
     medži
    -0.74
     Madi
    -0.73
     komfor
    -0.71
     Gub
    -0.70
     roux
    -0.69
     verze
    -0.69
    charAt
    -0.68
     gebre
    -0.68
    Abuse
    -0.68
    POSITIVE LOGITS
     MCK
    1.52
    BK
    1.43
    NK
    1.39
    DK
    1.38
     NK
    1.35
    FK
    1.33
     DK
    1.27
     McKenna
    1.27
     BK
    1.27
    GK
    1.26
    Activations Density 0.053%

    No Known Activations