© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112191
    Prev
    Next
    INDEX
    Explanations

    Woody Allen, and whatnot

    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_10/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
    ')
    -2.55
    
    -2.44
    -2.39
     \&
    -2.39
    \%)
    -2.28
    牁
    -2.28
    𝕿
    -2.27
    镒
    -2.23
    
    -2.20
    珢
    -2.09
    POSITIVE LOGITS
    or
    3.27
    ar
    2.33
     become
    2.27
    ?’
    2.23
    寕
    2.17
            
    2.16
     інших
    2.11
    s
    2.08
    ’;
    2.08
    When
    2.03
    Activations Density 0.001%
    No Known Activations