© 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. 64880
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and code comments

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

    The neuron fires strongly on standalone hyphens used as list‐item or entry markers.

    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
     mélanger
    -1.31
     distinguer
    -1.27
     avancer
    -1.27
     türkiye
    -1.26
     occuper
    -1.23
     diriger
    -1.22
     imprimer
    -1.20
     fotó
    -1.20
     bascul
    -1.19
     anniversaire
    -1.17
    POSITIVE LOGITS
     G
    1.34
     F
    1.30
     S
    1.28
     A
    1.23
     C
    1.22
     O
    1.21
     with
    1.21
     M
    1.20
     P
    1.19
     R
    1.16
    Activations Density 0.000%

    No Known Activations