© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32649
    Prev
    Next
    INDEX
    Explanations

    API requests and models

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

    The neuron activates on occurrences of “param” in code identifiers or import paths (e.g. package or class names like QueryParam).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ‍♂️
    -0.94
     cantora
    -0.93
     when
    -0.93
    ‍♀️
    -0.93
     continue
    -0.92
     assemblies
    -0.89
     continued
    -0.88
    Documented
    -0.87
    catid
    -0.87
    Usual
    -0.86
    POSITIVE LOGITS
    ochond
    1.06
    geç
    1.01
    Ζ
    0.93
    ските
    0.93
    minar
    0.93
    tilage
    0.92
     beleid
    0.92
    ArgsConstructor
    0.92
    orical
    0.90
    omalies
    0.90
    Activations Density 0.003%

    No Known Activations