© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11183
    Prev
    Next
    INDEX
    Explanations

    columns with counts

    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
    quirrel
    -1.21
     receive
    -1.17
     already
    -1.07
     to
    -1.07
    dawg
    -0.95
     årene
    -0.95
     allerede
    -0.93
     procedures
    -0.93
     or
    -0.92
    😤
    -0.92
    POSITIVE LOGITS
    今は
    1.20
    ctico
    1.13
    Галерея
    1.12
    ―――
    1.11
    without
    1.05
    three
    1.04
     combusti
    1.03
    最近の
    1.02
    本当は
    1.02
    1.01
    Activations Density 0.005%

    No Known Activations