© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32071
    Prev
    Next
    INDEX
    Explanations

    code structures and data initialization

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

    This neuron fires on prominent header or title tokens—e.g. uppercase or initial-cap words and code directives that mark the start of sections (like “#include,” section titles, class/namespace names, and other header‐style labels).

    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
    ণ
    -0.84
     těž
    -0.70
    oshi
    -0.68
    isé
    -0.68
     плю
    -0.68
     channel
    -0.67
    čně
    -0.65
    骐
    -0.65
     лекарства
    -0.65
    кус
    -0.65
    POSITIVE LOGITS
    ller
    0.72
     jon
    0.72
    妈妈
    0.71
    Moses
    0.70
     Chúa
    0.70
     滝
    0.69
     mama
    0.68
     .,
    0.68
    तो
    0.68
    evo
    0.67
    Activations Density 0.034%

    No Known Activations