© 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. 4381
    Prev
    Next
    INDEX
    Explanations

    academic text with citations

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

    The neuron selectively activates on specialized scientific or technical noun phrases (e.g. drug names, materials‐science terms, clinical measurements, and other domain‐specific jargon).

    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
     に関する
    -1.38
     について
    -1.20
     broader
    -1.17
     erweiter
    -1.15
    <h2>
    -1.15
     l
    -1.15
     nunmehr
    -1.14
     You
    -1.13
     a
    -1.11
    她就
    -1.09
    POSITIVE LOGITS
     [
    5.22
     $[
    3.19
    [
    3.13
    }[
    3.03
    '][
    2.16
    )[
    1.91
    ()[
    1.90
     [
    1.89
    ?[
    1.85
    [$
    1.82
    Activations Density 0.188%

    No Known Activations