© 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. 128332
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for leading whitespace (indentation) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    public interface definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ALSO
    -1.27
     also
    -1.15
     également
    -1.10
     aveva
    -1.04
     também
    -1.04
    همچنین
    -1.02
     sconfit
    -0.99
    Litteratur
    -0.99
    لباس
    -0.99
     reflexiones
    -0.97
    POSITIVE LOGITS
     such
    1.16
     (
    1.10
    void
    1.09
     Германии
    1.05
    '
    1.02
    /
    1.00
     adaptées
    0.99
     lopez
    0.98
     void
    0.96
    (
    0.96
    Activations Density 0.005%

    No Known Activations