© 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. 67061
    Prev
    Next
    INDEX
    Explanations

    other, others, miscellaneous

    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
    reebok
    -1.11
    clique
    -1.08
    sneaker
    -1.07
    waffle
    -1.03
    cree
    -1.02
    pañol
    -1.01
     menengah
    -0.98
     kwiat
    -0.97
    comedy
    -0.96
    ┚
    -0.95
    POSITIVE LOGITS
     other
    1.54
     any
    1.11
     including
    1.09
    其他
    1.07
     miscellaneous
    1.05
    อื่น
    1.01
     anything
    1.00
    other
    1.00
     category
    0.95
     unspecified
    0.93
    Activations Density 0.022%

    No Known Activations