© 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. 7486
    Prev
    Next
    INDEX
    Explanations

    break, open, potential, in

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

    The neuron flags the single most salient (uncommon or information‐rich) token in each text segment.

    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
    न्तर
    0.80
    मता
    0.79
     Τα
    0.79
    Ӯ
    0.77
    科学家
    0.77
    நுட்ப
    0.77
    মধ
    0.73
    谭
    0.73
     fracturing
    0.72
    ﻓ
    0.72
    POSITIVE LOGITS
    s
    0.85
    )";
    0.79
    }):
    0.79
    t
    0.78
    ่อน
    0.75
    Sc
    0.74
    ServiceInterface
    0.74
    Fiber
    0.74
    )").
    0.74
    room
    0.73
    Activations Density 0.000%

    No Known Activations