© 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. 8167
    Prev
    Next
    INDEX
    Explanations

    io libraries

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

    The neuron is highly activated by the token “io” in import or load statements (i.e. it flags occurrences of the “io” package prefix).

    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
    $,
    -2.55
    i
    -2.53
    E
    -2.48
    ’
    -2.48
    jsonwebtoken
    -2.41
    ’,
    -2.38
    and
    -2.30
    by
    -2.27
    section
    -2.27
     ,
    -2.23
    POSITIVE LOGITS
    你和
    2.45
    Ꮞ
    2.25
     participe
    2.22
    punkten
    2.19
    枥
    2.16
     afront
    2.14
    튿
    2.13
    熥
    2.09
    ㌘
    2.08
     armazen
    2.05
    Activations Density 0.025%

    No Known Activations