© 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. 40-GEMMASCOPE-2-RES-262K
    7. 6355
    Prev
    Next
    INDEX
    Explanations

    start of topic

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

    This neuron detects user requests/commands — prompts asking the model to perform a task or provide information (i.e., utterances that pose a request or instruction).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    common function words in user instructions (articles, prepositions, and generic quantifiers).

    oai_token-act-pair · gpt-5Triggered 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
    ↵
    0.40
     s
    0.32
     v
    0.32
    h
    0.32
     t
    0.31
     the
    0.31
    (
    0.31
     (
    0.31
     and
    0.30
    it
    0.30
    POSITIVE LOGITS
     уйнау
    0.40
    ayvachi
    0.33
     фараз
    0.31
    ದಗ
    0.31
     ইয়াহিয়ার
    0.30
    ओएस
    0.30
     imasmim
    0.30
    ጵ
    0.29
     بازیکن
    0.29
     پرومو
    0.29
    Activations Density 0.068%

    No Known Activations