© 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. 10-GEMMASCOPE-RES-131K
    7. 129127
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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
    9
    -1.95
    凩
    -1.88
    section
    -1.76
    7
    -1.68
    3
    -1.66
    潆
    -1.61
    跸
    -1.59
    崛
    -1.55
    ET
    -1.55
    AT
    -1.55
    POSITIVE LOGITS
     stör
    1.92
    ITAN
    1.85
    שלום
    1.84
    gencias
    1.82
     gä
    1.80
     betale
    1.79
    фай
    1.78
    ꯳
    1.77
    鯓
    1.70
     argentinos
    1.70
    Activations Density 0.052%

    No Known Activations