© 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. 15186
    Prev
    Next
    INDEX
    Explanations

    Some following examples

    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
     rast
    -1.20
    また
    -1.16
     lulus
    -1.14
     السياس
    -1.13
     trak
    -1.11
    jualan
    -1.09
     infine
    -1.07
     turist
    -1.07
     animali
    -1.05
     orice
    -1.05
    POSITIVE LOGITS
     have
    1.75
     people
    1.53
     times
    1.44
     know
    1.31
     things
    1.30
     kvůli
    1.30
    のことを
    1.26
     think
    1.25
     esquecer
    1.23
     would
    1.22
    Activations Density 0.048%

    No Known Activations