© 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. 92209
    Prev
    Next
    INDEX
    Explanations

    code and legal text

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

    The neuron fires on code‐ or data‐style tokens—especially identifiers and numeric constants (e.g. library names, version numbers, years).

    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
    हीं
    -0.69
     diva
    -0.67
     pneum
    -0.67
    Lunes
    -0.66
     Leben
    -0.65
    Bz
    -0.64
    estinian
    -0.64
    ystick
    -0.64
     superstructure
    -0.63
    AUTOR
    -0.61
    POSITIVE LOGITS
     метр
    0.73
    ház
    0.72
     Empfindung
    0.71
    verhältnisse
    0.69
     Mallorca
    0.68
    PEL
    0.67
     insanların
    0.67
    Trend
    0.67
    ichten
    0.67
    ICT
    0.65
    Activations Density 0.072%

    No Known Activations