© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116663
    Prev
    Next
    INDEX
    Explanations

    numbered sections and code

    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
    es
    -1.02
    getD
    -1.02
     coś
    -0.95
     enduro
    -0.94
     prerog
    -0.93
     afore
    -0.86
     again
    -0.86
     Df
    -0.85
     niacin
    -0.83
     Again
    -0.83
    POSITIVE LOGITS
     døde
    1.03
     akty
    0.97
     pisze
    0.97
     bluz
    0.94
     adicionales
    0.94
     vores
    0.93
    hæng
    0.93
     farba
    0.91
     gamla
    0.91
     rubia
    0.91
    Activations Density 0.003%

    No Known Activations