© 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. 22-GEMMASCOPE-RES-131K
    7. 15073
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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_22/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
     so
    -1.64
     should
    -1.49
     that
    -1.42
     could
    -1.42
     if
    -1.37
     any
    -1.30
     what
    -1.30
     this
    -1.30
     would
    -1.30
     can
    -1.27
    POSITIVE LOGITS
    惴
    1.33
    踉
    1.29
    ureusement
    1.28
    臵
    1.26
    issait
    1.25
     siè
    1.25
     feront
    1.25
    榇
    1.25
     verborgen
    1.25
     verhind
    1.24
    Activations Density 0.011%

    No Known Activations