© 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. 57792
    Prev
    Next
    INDEX
    Explanations

    list items and references

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

    The neuron fires on specialized academic or technical jargon—especially terms related to research methodology and guidelines (e.g. “guidelines,” “approach,” “coverage,” “trials,” “selection,” “analysis”).

    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
     fi
    -1.24
    fi
    -1.16
     fl
    -1.12
     first
    -1.05
    fl
    -0.96
    \'
    -0.95
    /}.
    -0.92
    ଘ
    -0.87
    髙
    -0.85
    ⼀
    -0.84
    POSITIVE LOGITS
    ◊
    1.15
     {{{
    1.00
    [[
    0.97
     {*}
    0.95
     [\
    0.95
     [[
    0.93
     [,
    0.91
    $[
    0.91
    [-]
    0.86
    {{{
    0.85
    Activations Density 0.591%

    No Known Activations