© 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. 34-GEMMASCOPE-RES-131K
    7. 70312
    Prev
    Next
    INDEX
    Explanations

    include guards and headers

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

    The neuron fires on tokens that are all‐caps identifiers or standalone numbers (e.g. macros, version numbers, years, license codes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     LIABLE
    -1.12
    templateUrl
    -1.03
    tomatik
    -1.02
    formerly
    -1.02
    примеча
    -1.02
    endmodule
    -1.00
    père
    -0.96
    }
    -0.96
    ροφο
    -0.95
    ˃
    -0.95
    POSITIVE LOGITS
     jezt
    1.11
    (!__
    1.04
     alluring
    1.04
    最后由
    1.03
     zowel
    1.02
    ocidad
    1.02
    ratory
    1.02
     brimming
    1.02
     Tecn
    1.02
     vooral
    1.02
    Activations Density 0.134%

    No Known Activations