© 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. 31450
    Prev
    Next
    INDEX
    Explanations

    binary options or licenses

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

    The neuron strongly activates on tokens that are numeric, punctuation, or code‐style symbols—basically numbers, commas, version numbers, dollar signs, and other programming-style tokens.

    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
    geschwindigkeit
    -0.68
     tradiciones
    -0.66
    liest
    -0.65
    ❞
    -0.65
    iana
    -0.65
    Gross
    -0.63
     periodista
    -0.63
    wor
    -0.63
     Isaac
    -0.62
    **
    -0.61
    POSITIVE LOGITS
    Scy
    0.81
     Breeders
    0.79
     Boi
    0.77
     Colette
    0.74
    ophthal
    0.73
     скри
    0.73
     architectural
    0.73
    ﺻ
    0.69
    颜
    0.69
     Álvarez
    0.69
    Activations Density 0.037%

    No Known Activations