© 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. 77297
    Prev
    Next
    INDEX
    Explanations

    p values

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

    The neuron selectively activates on numeric tokens (e.g. statistical values, p‐values, measurements), i.e. digits and number expressions.

    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
     relacionada
    -0.84
     mał
    -0.80
    虱
    -0.79
     Aufbau
    -0.78
    Ọ
    -0.77
     fieltro
    -0.77
    مي
    -0.76
     specifications
    -0.76
    `]
    -0.76
     tė
    -0.75
    POSITIVE LOGITS
     vehic
    0.90
     Dois
    0.88
     ROUT
    0.86
    🏑
    0.86
     compara
    0.86
     Prism
    0.85
     Halley
    0.84
     annon
    0.82
    责编
    0.82
     combus
    0.80
    Activations Density 0.014%

    No Known Activations