© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19013
    Prev
    Next
    INDEX
    Explanations

    structured data examples

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

    The neuron activates on numeric tokens—especially multi-digit or numeric values (numbers/floating-point tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    痉
    0.50
    不超过
    0.46
    ycled
    0.41
    stanbul
    0.41
     Новосибир
    0.41
     gestation
    0.41
     Casting
    0.40
     Dusty
    0.40
    बद्ध
    0.39
     suốt
    0.39
    POSITIVE LOGITS
    Sa
    0.49
    landing
    0.46
    Η
    0.46
     glider
    0.45
    mixer
    0.45
    agno
    0.45
    Σ
    0.44
     Corvette
    0.44
    љено
    0.44
    ת
    0.43
    Activations Density 0.000%

    No Known Activations