© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16149
    Prev
    Next
    INDEX
    Explanations

    parts of sequences

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

    This neuron fires on words that immediately precede floating-point numeric values (i.e. tokens right before a decimal number).

    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
    ){
    0.79
    که
    0.75
    ce
    0.72
    ore
    0.71
    مو
    0.68
    right
    0.68
     escort
    0.66
    𝘯
    0.66
    k
    0.65
    𝘳
    0.65
    POSITIVE LOGITS
     होती
    0.93
     인한
    0.88
     禁止
    0.88
     Inhalte
    0.86
    alé
    0.86
     콘텐츠
    0.85
    मियल
    0.83
    椹
    0.82
     භාවිතා
    0.82
    Einstellungen
    0.82
    Activations Density 0.000%

    No Known Activations