© 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. 128370
    Prev
    Next
    INDEX
    Explanations

    There is

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

    The neuron activates on import statements (especially wildcard “.*” imports).

    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
     is
    -2.97
     &
    -2.44
    辚
    -2.41
     to
    -2.31
    ichtete
    -2.28
    鲀
    -2.23
    providedIn
    -2.22
    聍
    -2.22
    expédition
    -2.17
    いえば
    -2.16
    POSITIVE LOGITS
    .*;
    3.34
    .*;
    2.86
     Они
    2.52
    寕
    2.34
    Ᏺ
    2.34
    chnung
    2.28
     Перейти
    2.19
    jenigen
    2.19
    ,:
    2.16
    衚
    2.14
    Activations Density 0.002%

    No Known Activations