© 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. 22-GEMMASCOPE-RES-131K
    7. 131022
    Prev
    Next
    INDEX
    Explanations

    Clinical, Battle, Q

    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_22/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
     MyBatis
    -1.21
     tenis
    -1.16
     sintomas
    -1.15
    我們
    -1.13
     dager
    -1.12
     avantage
    -1.09
     Corbu
    -1.09
    cised
    -1.06
    !");
    -1.05
    vde
    -1.05
    POSITIVE LOGITS
     his
    1.14
     total
    1.06
     traditional
    1.05
     jeweils
    1.04
     g
    1.04
     często
    1.03
     customary
    1.02
    事に
    1.02
     Traditional
    0.99
    dot
    0.96
    Activations Density 0.007%

    No Known Activations