© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14515
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

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

    the neuron detects numeric tokens or tokens containing numeric/measurement values (numbers, parameter values, digits).

    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_40_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
    வுக
    0.49
    ancı
    0.47
    Meeting
    0.44
    ValueError
    0.44
    Tipo
    0.43
    ţional
    0.42
    豎
    0.40
    verso
    0.40
    Tres
    0.40
     चाहिए
    0.40
    POSITIVE LOGITS
     waves
    0.45
     g
    0.43
     $
    0.40
     bied
    0.40
     bize
    0.40
     pad
    0.39
    ampunk
    0.38
     ass
    0.38
     simplification
    0.38
     kittens
    0.38
    Activations Density 0.000%

    No Known Activations