© 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. 39380
    Prev
    Next
    INDEX
    Explanations

    hunt and hunting

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

    The neuron activates on occurrences of the root “hunt” (e.g. hunt, hunting, Huntington) in words.

    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
    Y
    -2.30
    2
    -2.23
    ”
    -2.11
    T
    -2.08
     måste
    -2.03
    ネットで
    -2.02
    なかな
    -1.98
    our
    -1.98
    股东
    -1.97
     Mehrheit
    -1.97
    POSITIVE LOGITS
    铩
    2.66
    玢
    2.50
    ри
    2.39
    花板
    2.38
    struzione
    2.33
    anthene
    2.30
     szary
    2.27
    wallpapers
    2.27
     biała
    2.25
    ные
    2.22
    Activations Density 0.012%

    No Known Activations