© 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. 10-GEMMASCOPE-RES-131K
    7. 99420
    Prev
    Next
    INDEX
    Explanations

    Dial One

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

    This neuron fires on standalone punctuation “separator” tokens (e.g. lines or tokens of only ellipses, blank‐line markers, or similar standalone punctuation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ΅
    -1.56
     Pues
    -1.54
    していました
    -1.53
    媃
    -1.52
    WINTER
    -1.52
    ڤ
    -1.51
    rra
    -1.47
    ܜ
    -1.47
     Estoy
    -1.47
    stacle
    -1.47
    POSITIVE LOGITS
    One
    2.05
    。
    1.73
    </sup>
    1.54
    {
    1.52
    </h4>
    1.48
    "
    1.46
    Start
    1.45
    1
    1.44
     also
    1.43
    Time
    1.41
    Activations Density 0.006%

    No Known Activations