© 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. 130058
    Prev
    Next
    INDEX
    Explanations

    number, identifier, or count

    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
    :");
    -2.19
    CHREIB
    -2.16
    ౖ
    -2.11
    viembre
    -1.96
    tafogo
    -1.89
    ghalaya
    -1.88
     zustand
    -1.84
    because
    -1.83
    まえ
    -1.81
    sedown
    -1.77
    POSITIVE LOGITS
    9
    2.02
    ?"
    2.02
    
    1.91
    CurtirCurtir
    1.85
    ogram
    1.84
    かわい
    1.83
    訁
    1.82
    缡
    1.81
    厹
    1.81
    8
    1.81
    Activations Density 0.019%

    No Known Activations