© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99015
    Prev
    Next
    INDEX
    Explanations

    nut contexts

    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
    of
    -3.41
    谖
    -3.00
    婳
    -2.88
    饃
    -2.48
    凊
    -2.45
    
    -2.36
    襌
    -2.36
    떳
    -2.36
     наш
    -2.33
    himself
    -2.33
    POSITIVE LOGITS
    ются
    2.66
    \
    2.63
    </h1>
    2.58
     When
    2.53
     opens
    2.45
    餮
    2.42
     firmado
    2.42
    ThemeOverlay
    2.39
     In
    2.34
    dır
    2.28
    Activations Density 0.006%

    No Known Activations