© 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. 8095
    Prev
    Next
    INDEX
    Explanations

    human body parts

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

    This neuron fires on tokens that begin new lines/blocks of text—i.e. paragraph‐ or segment-initial words.

    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
    젼
    0.86
    жная
    0.85
    щают
    0.85
    няют
    0.81
    дары
    0.79
     waveguides
    0.79
    дная
    0.79
    жных
    0.75
    ังก
    0.75
    няет
    0.74
    POSITIVE LOGITS
    We
    0.89
    Efter
    0.87
    Während
    0.86
    T
    0.86
    Pablo
    0.85
     peintre
    0.82
    Não
    0.82
    Dopo
    0.82
    She
    0.82
    Ε
    0.82
    Activations Density 0.001%

    No Known Activations