© 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. 72983
    Prev
    Next
    INDEX
    Explanations

    run only once

    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
    ilistic
    -0.90
     adipo
    -0.87
    day
    -0.84
     during
    -0.83
     months
    -0.82
     season
    -0.82
    일에
    -0.82
     to
    -0.81
     day
    -0.81
     They
    -0.80
    POSITIVE LOGITS
    予報
    0.97
     vlas
    0.97
     esigen
    0.85
    FFECT
    0.80
     uyt
    0.80
    Licht
    0.79
     ocz
    0.79
     useAuth
    0.79
     napisał
    0.78
    Reactions
    0.78
    Activations Density 0.064%

    No Known Activations