© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92988
    Prev
    Next
    INDEX
    Explanations

    code and legal disclaimers

    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
    COUNTS
    -0.75
    
    -0.72
    Herald
    -0.72
    lacian
    -0.71
     median
    -0.71
     Dafür
    -0.69
    lawful
    -0.69
     convir
    -0.68
    oherty
    -0.66
    اعمال
    -0.66
    POSITIVE LOGITS
     admonition
    0.77
     Thunderbird
    0.77
     tungkol
    0.76
     mathématiques
    0.73
     naruto
    0.72
     bmw
    0.71
     Kurs
    0.69
     morocco
    0.69
    gala
    0.68
     veal
    0.68
    Activations Density 0.050%

    No Known Activations