© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1604
    Prev
    Next
    INDEX
    Explanations

    end of sentence questions

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

    The neuron detects numeric tokens—numbers, dates/times, version numbers, or other digit-heavy tokens (long numeric sequences).

    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
     aquelas
    0.45
     aquela
    0.44
     aquel
    0.43
     aqueles
    0.43
     aquellas
    0.42
     aquellos
    0.41
    嘛
    0.41
    那样
    0.40
     disclosures
    0.40
     aquele
    0.39
    POSITIVE LOGITS
    怎么办
    0.73
    HELP
    0.72
     HELP
    0.71
     Help
    0.69
    help
    0.64
     help
    0.63
     Tried
    0.62
     Worse
    0.59
    tried
    0.59
     tried
    0.59
    Activations Density 0.009%

    No Known Activations