© 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. 7234
    Prev
    Next
    INDEX
    Explanations

    signature, attraction, verification

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

    This neuron fires on tokens that begin new sections or standalone headings (i.e. line-initial or title-style 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
     тоже
    0.82
    verdad
    0.77
     właśnie
    0.75
     наверное
    0.71
    К
    0.71
     είναι
    0.70
    dreams
    0.69
     ♪
    0.68
     врач
    0.68
     expresó
    0.68
    POSITIVE LOGITS
     transactional
    0.70
     subsequent
    0.65
     surrogate
    0.65
    ಮಾನ
    0.64
     ambiguities
    0.64
     가운데
    0.64
     verification
    0.63
     questionable
    0.63
     Labels
    0.63
     Singleton
    0.63
    Activations Density 0.000%

    No Known Activations