© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5540
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting mentions of small hardware or attachment parts (e.g. hooks, knobs, levers, strings, posts).

    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_24_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
     показатели
    0.78
     اعداد
    0.74
     Data
    0.73
     plików
    0.72
    覽
    0.70
     moindre
    0.70
    čkog
    0.70
     ambientale
    0.70
    மதி
    0.67
     organismes
    0.67
    POSITIVE LOGITS
     gripper
    0.94
     clasp
    0.93
    Scissors
    0.92
     straps
    0.92
     shank
    0.88
     protruding
    0.85
     lembut
    0.83
    付き
    0.82
    🦵
    0.82
     scissors
    0.81
    Activations Density 0.000%

    No Known Activations