© 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. 73638
    Prev
    Next
    INDEX
    Explanations

    dates preceding titles

    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
    fillment
    -1.63
     Hinsicht
    -1.58
     you
    -1.58
    notch
    -1.55
     isn
    -1.53
    paedia
    -1.53
     localidades
    -1.52
    neling
    -1.52
    micamente
    -1.51
     Filosof
    -1.50
    POSITIVE LOGITS
    涐
    1.71
    我們
    1.60
    我們的
    1.41
     deň
    1.37
    -
    1.35
    怀疑
    1.35
    瘆
    1.35
    pijama
    1.31
     wiederholt
    1.28
    人們
    1.28
    Activations Density 0.159%

    No Known Activations