© 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. 112152
    Prev
    Next
    INDEX
    Explanations

    in tune with

    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
     '/';
    -2.25
    );
    -2.02
    
    -1.98
     ''),
    -1.89
     '-';
    -1.84
     getestet
    -1.84
    箪
    -1.83
     ''}
    -1.80
     einwand
    -1.79
     رضا
    -1.71
    POSITIVE LOGITS
     участке
    1.84
    “
    1.81
     jadx
    1.63
    ments
    1.59
     japones
    1.58
    am
    1.58
     死
    1.55
    
    1.55
     firstly
    1.53
     oiseau
    1.53
    Activations Density 0.005%

    No Known Activations