© 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. 7720
    Prev
    Next
    INDEX
    Explanations

    common ancestor relations

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

    The neuron fires most strongly on section‐ or headline‐style keywords (including opening punctuation) that mark the start of a new topic or title.

    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
    م
    0.73
    u
    0.71
    curvature
    0.68
    Equals
    0.64
    ',
    0.64
    с
    0.64
     marca
    0.63
    OT
    0.61
    ോ
    0.61
    ','
    0.60
    POSITIVE LOGITS
     phospholip
    0.93
     lukewarm
    0.93
     arrondies
    0.90
    ၆
    0.90
    щины
    0.90
     adecuados
    0.90
     adecuada
    0.83
     spô
    0.83
     birefring
    0.83
     aggressively
    0.82
    Activations Density 0.000%

    No Known Activations