© 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. 68114
    Prev
    Next
    INDEX
    Explanations

    initialization calls and objects

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

    This neuron fires on programming identifiers—especially method or function names in CamelCase or mixedCase.

    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
    M
    -2.09
     einschließlich
    -2.02
    OUTUBE
    -1.95
     devido
    -1.92
    VIATIONS
    -1.91
     "}";
    -1.89
    рії
    -1.88
    including
    -1.88
    jenige
    -1.84
    要注意
    -1.81
    POSITIVE LOGITS
     برای
    2.20
    edere
    2.19
    的话
    2.16
    0
    2.03
    ma
    2.02
    ed
    2.00
    也
    1.99
    就
    1.98
    ቼ
    1.95
    ions
    1.93
    Activations Density 0.000%

    No Known Activations