© 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. 15737
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to technical file‐format and media‐operation terms (e.g. transcoding, renaming, mp3, pcm, plays, unsupported format).

    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
    I
    0.95
    l
    0.94
    we
    0.87
    We
    0.84
    A
    0.84
    ל
    0.84
    Okay
    0.82
    r
    0.82
    et
    0.82
    there
    0.82
    POSITIVE LOGITS
     menimbulkan
    0.75
     berbahaya
    0.74
     kinerja
    0.73
     elevado
    0.73
     menyebabkan
    0.70
     hingegen
    0.69
     uncontrolled
    0.68
     toxicants
    0.68
     unnecessarily
    0.65
     vrijed
    0.65
    Activations Density 16.491%

    No Known Activations