© 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. 8100
    Prev
    Next
    INDEX
    Explanations

    Ajax, ASUS, blouse types

    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
    あるので
    -2.52
    袿
    -2.36
    
    -2.36
    .”
    -2.34
    後記
    -2.25
    rália
    -2.20
     espac
    -2.20
    睺
    -2.19
    縠
    -2.19
    ージョン
    -2.17
    POSITIVE LOGITS
    {
    3.77
    2.72
     είναι
    2.69
    al
    2.63
    }
    2.50
    a
    2.48
    5
    2.41
    通过
    2.31
    g
    2.30
    在
    2.27
    Activations Density 0.004%
    No Known Activations