© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11025
    Prev
    Next
    INDEX
    Explanations

    section headers or markers

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

    The neuron fires on occurrences of the identifier “LOCAL” in uppercase, as in Makefile or build‐script variable names (e.g. LOCAL_PATH, LOCAL_MODULE).

    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
     with
    -1.78
    怪我
    -1.75
     Çok
    -1.63
     It
    -1.62
    ⸎
    -1.61
    Tengo
    -1.58
    鉝
    -1.55
    2
    -1.54
    satunya
    -1.54
     Pertama
    -1.54
    POSITIVE LOGITS
    "
    2.16
    ’
    2.14
     estándares
    1.70
    읗
    1.60
    '
    1.60
     ダーク
    1.53
    b
    1.53
     ebenso
    1.52
    to
    1.51
    as
    1.49
    Activations Density 0.000%

    No Known Activations