© 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. 85133
    Prev
    Next
    INDEX
    Explanations

    specific initial phrases

    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
    1
    -4.19
    2
    -4.13
    0
    -3.95
    3
    -3.59
    7
    -3.34
    6
    -3.19
    -
    -3.08
    4
    -2.94
    9
    -2.92
    5
    -2.84
    POSITIVE LOGITS
    羕
    2.95
    釹
    2.89
    垍
    2.84
    劼
    2.81
    幛
    2.77
    ;'>
    2.75
    𖣘
    2.73
    
    2.72
     organizador
    2.69
    糨
    2.69
    Activations Density 0.003%

    No Known Activations