© 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. 7022
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    This neuron detects metadata labels in media posts (e.g. upload times, durations, view counts, source attributions).

    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
    錄
    0.70
    說
    0.70
    這一
    0.69
     Geoff
    0.68
    tions
    0.68
     tua
    0.68
     ç
    0.67
    犾
    0.65
    ments
    0.65
    些
    0.64
    POSITIVE LOGITS
    imiento
    0.86
     машиналары
    0.84
    پار
    0.78
    QUID
    0.74
    чением
    0.73
    ikus
    0.72
    oğlu
    0.72
    avoro
    0.71
     সাজেশন
    0.71
    ujo
    0.71
    Activations Density 0.002%

    No Known Activations