© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71962
    Prev
    Next
    INDEX
    Explanations

    programming and code libraries

    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
     from
    -1.16
     our
    -1.16
    besar
    -1.09
    hijab
    -1.06
     žaid
    -1.04
     that
    -1.01
     had
    -0.98
    escar
    -0.97
    jangan
    -0.97
     leveraging
    -0.96
    POSITIVE LOGITS
    particularly
    1.20
    town
    1.12
    tic
    1.10
    are
    1.09
    cha
    1.08
    iz
    1.08
    l
    1.08
    one
    1.07
    especially
    1.07
    the
    1.05
    Activations Density 0.077%

    No Known Activations