© 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. 22-GEMMASCOPE-RES-131K
    7. 33515
    Prev
    Next
    INDEX
    Explanations

    code keywords and declarations

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

    The neuron is triggered by leading whitespace or tab‐style indentation in code (i.e. code block indentation).

    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
     if
    -1.80
     when
    -1.56
     it
    -1.42
     both
    -1.26
     even
    -1.24
     any
    -1.24
    توضیحات
    -1.20
     as
    -1.19
     each
    -1.16
     because
    -1.16
    POSITIVE LOGITS
     ledit
    1.13
     mantenga
    1.09
    鲧
    1.09
     relatif
    1.07
    zwischen
    1.05
    źródło
    1.05
     ersche
    1.04
    orting
    1.03
     caribou
    1.03
     pru
    1.02
    Activations Density 0.010%

    No Known Activations