© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8342
    Prev
    Next
    INDEX
    Explanations

    fish

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

    The neuron strongly activates for mentions of “fish” or fish-related compounds (e.g. fish-eye, fish-tail).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    τρι
    0.63
    一份
    0.59
    পর
    0.59
    SIE
    0.59
    ഞ
    0.58
    RENC
    0.58
    UCE
    0.57
     brain
    0.57
     assistance
    0.57
    دی
    0.57
    POSITIVE LOGITS
    🎣
    0.75
    bowl
    0.72
    釣り
    0.66
     Fishing
    0.65
     Fischer
    0.65
     Flies
    0.63
    竿
    0.61
     Fish
    0.61
     Hunting
    0.61
    hooks
    0.59
    Activations Density 0.067%

    No Known Activations