© 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. 54475
    Prev
    Next
    INDEX
    Explanations

    code keywords and declarations

    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
     REPLIES
    -0.95
     CONTRIBUTOR
    -0.90
     arrog
    -0.85
    uchungen
    -0.84
     realizes
    -0.84
    국
    -0.83
     RELATIONS
    -0.83
    อบ
    -0.83
    brille
    -0.83
     configureStore
    -0.82
    POSITIVE LOGITS
     and
    1.03
    ₓ
    1.03
    </b>
    0.93
     usein
    0.91
    дио
    0.91
    شير
    0.91
     или
    0.90
    結構
    0.90
     osal
    0.90
     أو
    0.89
    Activations Density 0.015%

    No Known Activations