© 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. 70675
    Prev
    Next
    INDEX
    Explanations

    field or free or alone

    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
     other
    -1.04
    8
    -1.01
    4
    -0.95
     andet
    -0.86
     Sert
    -0.85
    那边
    -0.85
     etc
    -0.84
     various
    -0.83
     superman
    -0.83
    чие
    -0.82
    POSITIVE LOGITS
    %">
    1.08
    oneof
    1.00
    μμα
    0.96
    
    0.95
    bno
    0.95
    
    0.92
    monių
    0.90
    therefore
    0.90
    ront
    0.89
    ctober
    0.88
    Activations Density 0.114%

    No Known Activations