© 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. 54431
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and code structure

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

    This neuron activates on programming identifiers or symbols—especially multiword/camel- or Pascal-cased names—in code snippets.

    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
     its
    -1.23
    に入れる
    -1.17
    ulates
    -1.09
     entraîner
    -1.02
     behaviour
    -1.00
    Denote
    -0.99
    weren
    -0.96
    要么
    -0.94
    scoring
    -0.94
     gouttes
    -0.93
    POSITIVE LOGITS
     will
    1.34
     mainly
    1.13
     like
    1.06
     mostly
    1.04
     also
    1.00
     may
    1.00
     only
    0.97
    Baja
    0.95
     might
    0.95
     probably
    0.94
    Activations Density 0.007%

    No Known Activations