© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62856
    Prev
    Next
    INDEX
    Explanations

    advertisement times and dates

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

    The neuron is selectively responding to programming‐style tokens and numeric literals (e.g. preprocessor directives like “#”, “include” statements, dates, times, and other numbers).

    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
     trá
    -0.69
    няется
    -0.67
    Prompt
    -0.66
     REGARD
    -0.66
    comer
    -0.66
    सि
    -0.65
    澄
    -0.65
    шення
    -0.65
     zare
    -0.64
     clé
    -0.64
    POSITIVE LOGITS
    nione
    0.82
    ┭
    0.78
    IsOpen
    0.75
    洇
    0.75
    juvant
    0.73
    acki
    0.72
    érieurs
    0.71
    bióticos
    0.71
    undos
    0.70
     مسی
    0.69
    Activations Density 0.048%

    No Known Activations