© 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. 13857
    Prev
    Next
    INDEX
    Explanations

    animal behavior, fights, or wrestling

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

    concepts related to animal behavior and social interactions in scientific research papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly fires on terminology referring to sentinel (guarding) behavior in social or group‐living animals.

    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
     your
    -1.87
     you
    -1.86
     then
    -1.84
     of
    -1.44
     shouldn
    -1.37
     consideración
    -1.31
    Mots
    -1.30
     penjual
    -1.27
    then
    -1.26
    你和
    -1.26
    POSITIVE LOGITS
     during
    1.75
    řejmě
    1.54
     jsem
    1.42
     their
    1.41
     individuelle
    1.34
     leur
    1.31
     activity
    1.30
     amorosa
    1.30
    ťa
    1.30
    RatingBar
    1.30
    Activations Density 0.170%

    No Known Activations