© 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. 39935
    Prev
    Next
    INDEX
    Explanations

    timeout or out

    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
    ,’
    -1.92
    ?”
    -1.90
    .”
    -1.88
    g
    -1.78
     she
    -1.76
     (‘
    -1.72
     tenets
    -1.71
    o
    -1.70
     those
    -1.63
    ponde
    -1.63
    POSITIVE LOGITS
    皛
    1.86
    骘
    1.80
     singuli
    1.80
    很赞
    1.78
     pauvreté
    1.77
    
    1.75
    重庆
    1.74
    洐
    1.74
    вка
    1.74
    ון
    1.73
    Activations Density 0.006%

    No Known Activations