© 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. 8451
    Prev
    Next
    INDEX
    Explanations

    button click action

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

    The neuron strongly activates on blog‐style metadata lines—tokens around dates, timestamps, “tagged in,” and similar post metadata markers.

    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
    ה
    0.86
    و
    0.81
    ня
    0.80
    flashlight
    0.78
    Medical
    0.74
    ження
    0.73
    itinéraire
    0.73
    ب
    0.71
     defaultValue
    0.69
    サイクル
    0.69
    POSITIVE LOGITS
    rared
    0.76
     vesting
    0.75
     Tô
    0.73
     bipolar
    0.71
     Chí
    0.70
     하기
    0.69
    ᄑ
    0.69
     logros
    0.68
     gossip
    0.68
    ইতে
    0.67
    Activations Density 0.000%

    No Known Activations