© 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. 32995
    Prev
    Next
    INDEX
    Explanations

    Aws, api, rest, protobuf, umi, Ice, Editor

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on tokens naming programming libraries, frameworks, or namespaces (e.g. AWS, Utils, ms-rest, Pulumi, wasm_bindgen) typically found in include/import lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     on
    -1.78
     from
    -1.70
     with
    -1.66
     epitom
    -1.60
     for
    -1.60
     or
    -1.55
     before
    -1.53
     Drž
    -1.43
     most
    -1.41
     tailored
    -1.41
    POSITIVE LOGITS
    particularly
    1.63
    approximately
    1.54
     カジュアル
    1.53
    potentially
    1.47
    could
    1.47
     ™
    1.44
    possibly
    1.44
     dando
    1.44
     essas
    1.43
    specifically
    1.43
    Activations Density 0.011%

    No Known Activations