© 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. 128333
    Prev
    Next
    INDEX
    Explanations

    code assignment and definition

    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
     any
    -1.70
    ありますか
    -1.20
     anything
    -1.19
     dores
    -1.19
     enough
    -1.13
     orice
    -1.11
     sufficient
    -1.09
     sveta
    -1.05
     sytu
    -1.05
     my
    -1.04
    POSITIVE LOGITS
    という
    1.05
    は
    1.02
    },{
    1.01
    ：@
    1.01
     =
    0.99
    Sqft
    0.98
    зывает
    0.98
    bigoplus
    0.93
    arons
    0.93
    这让
    0.93
    Activations Density 0.019%

    No Known Activations