© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10769
    Prev
    Next
    INDEX
    Explanations

    continuation, next steps, or further actions

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

    the neuron detects action-oriented instruction words—imperative verbs and step headings used in how-to or procedural text.

    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
     сооб
    0.14
    㝅
    0.14
     lawmakers
    0.14
     landowners
    0.13
    <unused277>
    0.13
    <unused2101>
    0.13
     devout
    0.13
    ῎
    0.13
    <unused301>
    0.13
    टकों
    0.12
    POSITIVE LOGITS
    '
    0.19
    ",
    0.19
    \
    0.17
    ↵
    0.17
    ',
    0.17
    .
    0.16
    ’
    0.16
     -
    0.16
    ().
    0.15
    =
    0.15
    Activations Density 0.114%

    No Known Activations