© 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. 10-GEMMASCOPE-RES-131K
    7. 44808
    Prev
    Next
    INDEX
    Explanations

    animals and hunting

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

    references to fish and game species in hunting and fishing contexts.

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

    This neuron detects mentions of specific fish species.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    lihood
    -1.40
    epar
    -1.34
    vr
    -1.32
    曏
    -1.30
    uation
    -1.27
    ↵↵
    -1.27
    iencias
    -1.27
    taker
    -1.27
    heds
    -1.25
     marti
    -1.23
    POSITIVE LOGITS
    adé
    1.57
    uniqlo
    1.48
    jesus
    1.35
    nintendo
    1.34
     speziellen
    1.33
    扪
    1.33
     cometer
    1.31
     establecer
    1.30
    Robbie
    1.27
    destroyAll
    1.27
    Activations Density 0.014%

    No Known Activations