© 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. 119118
    Prev
    Next
    INDEX
    Explanations

    policy guidelines and making

    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
     have
    -1.22
     utilize
    -1.03
     So
    -0.97
    …
    -0.95
    or
    -0.95
    ?
    -0.95
     rise
    -0.95
     loss
    -0.95
    依照
    -0.95
    end
    -0.92
    POSITIVE LOGITS
     policy
    1.73
     makers
    1.38
     POLICY
    1.31
    policy
    1.30
     Policies
    1.27
    Policy
    1.27
     Policy
    1.27
    "},
    
    1.23
    policies
    1.21
    making
    1.20
    Activations Density 0.015%

    No Known Activations