© 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. 4284
    Prev
    Next
    INDEX
    Explanations

    checking for existence

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

    The neuron detects numeric constants and related tokens (literal numbers and their associated assignment/value labels) in code or documentation.

    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
    iviato
    0.63
    разу
    0.63
    ɖ
    0.62
    ymmet
    0.61
    नंतर
    0.59
    jó
    0.59
    üssel
    0.59
     общество
    0.57
    ktrum
    0.57
    ꯁ
    0.57
    POSITIVE LOGITS
     bereits
    0.70
     existentes
    0.68
     bisher
    0.67
     existing
    0.66
    Existing
    0.66
    已有
    0.64
    既存
    0.64
     schon
    0.63
     laufen
    0.61
     기존
    0.61
    Activations Density 0.002%

    No Known Activations