© 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. 44385
    Prev
    Next
    INDEX
    Explanations

    spatial relation and length

    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
     This
    -2.72
     We
    -2.50
     At
    -2.44
     to
    -2.41
     You
    -2.41
     Also
    -2.08
     Not
    -2.08
     There
    -2.02
     But
    -1.99
     It
    -1.97
    POSITIVE LOGITS
    𓆏
    1.95
    麃
    1.88
     prenn
    1.86
    蟶
    1.82
     málaga
    1.80
    獁
    1.80
    說
    1.77
    鋨
    1.74
     Juin
    1.74
    ޚ
    1.73
    Activations Density 0.086%

    No Known Activations