© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26938
    Prev
    Next
    INDEX
    Explanations

    What happensWettingPak Kyong-samFurniture included

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

    This neuron responds to long runs of leading whitespace (indentation) in code or markup.

    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
     that
    -1.28
     sahiptir
    -1.24
     katk
    -1.23
     tervez
    -1.23
    ΙΣ
    -1.21
    ,:),
    -1.16
     astuces
    -1.15
    𓄹
    -1.15
    providedIn
    -1.15
     mieli
    -1.14
    POSITIVE LOGITS
     firs
    1.34
     then
    1.33
     subsequent
    1.27
     somewhat
    1.22
     successive
    1.20
     overly
    1.20
     insanely
    1.16
    aned
    1.15
     insane
    1.14
     ensuing
    1.13
    Activations Density 0.000%

    No Known Activations