© 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. 87264
    Prev
    Next
    INDEX
    Explanations

    BP Unfiltered, inhibition

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

    mathematical notation and symbols used in equations, matrices, and formulas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens (digits and numbers) appearing in text or equations.

    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
     بور
    -0.84
     břez
    -0.81
     casado
    -0.81
     Moi
    -0.81
    オンライン
    -0.81
    falt
    -0.77
    感到
    -0.77
    ठी
    -0.77
     moteur
    -0.76
    freund
    -0.76
    POSITIVE LOGITS
     I
    0.94
     A
    0.93
     D
    0.90
     W
    0.89
    اویر
    0.85
     P
    0.82
     Crisp
    0.80
     M
    0.78
     B
    0.78
     peme
    0.76
    Activations Density 0.012%

    No Known Activations