© 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. 22-GEMMASCOPE-RES-131K
    7. 95455
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and keywords

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

    The neuron detects standalone all-caps identifiers (constants) made up of uppercase letters and underscores.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    為に
    -1.76
    にします
    -1.62
    感じで
    -1.62
    corrhi
    -1.61
    こともあり
    -1.55
    providedIn
    -1.52
    の方に
    -1.50
    ときは
    -1.45
    さぁ
    -1.45
    ごとの
    -1.45
    POSITIVE LOGITS
    <bos>
    1.80
    を
    1.65
    がありますが
    1.60
    があります
    1.52
    但却
    1.48
    <0xA3>
    1.42
    動機
    1.41
    礎
    1.41
    や
    1.38
    そして
    1.38
    Activations Density 0.021%

    No Known Activations