© 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. 60345
    Prev
    Next
    INDEX
    Explanations

    code endings and directives

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

    The neuron fires on structural or directive markers in code and templates—e.g. preprocessor and region tags (#region, #endregion, #if/#endif) and template block directives ({% block … %}/{% endblock %}).

    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
     Also
    -1.08
     meint
    -1.02
     also
    -1.00
     It
    -0.99
     także
    -0.94
     také
    -0.89
     to
    -0.88
     iż
    -0.88
     likewise
    -0.87
    цією
    -0.87
    POSITIVE LOGITS
    ועל
    1.02
    ↵
    1.02
    vär
    0.99
    Количество
    0.98
     vatten
    0.97
    难受
    0.96
    OOTDTY
    0.95
     oreille
    0.93
     Nå
    0.93
    Bretagne
    0.92
    Activations Density 0.008%

    No Known Activations