© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9047
    Prev
    Next
    INDEX
    Explanations

    early or original

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

    The neuron fires strongly at the very first content word of a new paragraph or section—i.e. it flags the start of a fresh topical block.

    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
    ل
    0.88
    не
    0.76
     クラ
    0.73
    но
    0.71
    Attractive
    0.70
    Holding
    0.68
    CSP
    0.67
    स
    0.67
     および
    0.66
    で
    0.65
    POSITIVE LOGITS
     glycolysis
    0.86
     oxígeno
    0.84
     oxen
    0.79
     freighter
    0.76
     oxygen
    0.75
     templo
    0.75
     mundo
    0.75
     myeloid
    0.75
     myeloma
    0.75
     seventy
    0.74
    Activations Density 0.001%

    No Known Activations