© 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. 63235
    Prev
    Next
    INDEX
    Explanations

    documentation structure

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

    The neuron primarily detects numeric tokens (sequences of digits) such as version numbers, counts, headings, or other standalone numbers in the text.

    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
    İN
    -0.96
    ●
    -0.94
    ⠝
    -0.94
     män
    -0.93
    hånd
    -0.93
    setLength
    -0.92
    ästi
    -0.91
     artikel
    -0.90
    Ğ
    -0.90
     Liga
    -0.89
    POSITIVE LOGITS
    <code>
    1.77
    <sup>
    1.30
    <h3>
    1.25
    <h2>
    1.20
    <blockquote>
    1.17
    {%
    1.16
    <h1>
    1.14
    <sub>
    1.12
    <h4>
    1.03
     herzlich
    0.88
    Activations Density 0.027%

    No Known Activations