© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39231
    Prev
    Next
    INDEX
    Explanations

    .byte, Life insurance, Q:, A study, Regional Access

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

    This neuron fires on the standalone “.” token that marks assembly or assembler‐directive lines (e.g., the leading dot in “.byte”, “.align”, etc.).

    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
    providedIn
    -1.34
     ALL
    -1.26
     so
    -1.23
     FÜR
    -1.23
     aast
    -1.22
     would
    -1.21
    ції
    -1.20
     artikkelen
    -1.16
     JUST
    -1.15
     most
    -1.14
    POSITIVE LOGITS
    惴
    1.29
     singola
    1.23
     possibilidade
    1.14
     nimmer
    1.10
    広く
    1.09
     MATHEMAT
    1.09
    zęd
    1.08
    Bibliografie
    1.08
     probabilmente
    1.07
    ,?
    1.07
    Activations Density 0.000%

    No Known Activations