© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65906
    Prev
    Next
    INDEX
    Explanations

    code structure and configuration

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

    The neuron fires on code-oriented identifiers and technical names—i.e. multi-character uppercase or CamelCase tokens (e.g. class or constant names, acronyms, license/license-file references).

    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
     refusé
    -1.16
     mangá
    -1.09
     répondu
    -1.08
    \%)
    -1.07
     Italien
    -1.02
     Πολ
    -1.02
     kapit
    -1.00
     jugé
    -1.00
    |=
    -0.99
     kompakt
    -0.99
    POSITIVE LOGITS
    ";
    1.60
    ”;
    1.34
    ");
    1.22
     '';
    1.07
    ”.
    1.05
    id
    1.02
    ';
    1.02
    ;
    1.02
    ;</
    1.01
    [];
    1.00
    Activations Density 0.001%

    No Known Activations