© 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. 90885
    Prev
    Next
    INDEX
    Explanations

    code and documentation comments

    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
     perro
    -0.86
    rony
    -0.85
     overlook
    -0.84
    bruck
    -0.84
    IENCE
    -0.84
     שלהם
    -0.83
     Neust
    -0.83
    ropic
    -0.81
     تومان
    -0.80
    brar
    -0.80
    POSITIVE LOGITS
     Promise
    1.01
     tslint
    0.87
     ts
    0.85
     się
    0.84
    рку
    0.84
    Dermott
    0.82
     Ts
    0.81
     tóxic
    0.81
    usap
    0.80
     TS
    0.77
    Activations Density 0.006%

    No Known Activations