© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104359
    Prev
    Next
    INDEX
    Explanations

    locations

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

    This neuron detects the occurrence of the substring “enter” (as in “center,” “multicenter,” etc.) within tokens.

    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
     at
    -0.89
     that
    -0.83
     or
    -0.79
     anything
    -0.78
    ाले
    -0.77
     Céline
    -0.75
     its
    -0.75
     occupying
    -0.74
     whose
    -0.74
    jor
    -0.74
    POSITIVE LOGITS
     locations
    1.82
     sites
    1.52
    locations
    1.35
     Locations
    1.30
    sites
    1.27
    Sites
    1.23
    Locations
    1.18
     LOCATIONS
    1.18
     places
    1.17
     Sites
    1.15
    Activations Density 0.143%

    No Known Activations