© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3959
    Prev
    Next
    INDEX
    Explanations

    invitations to interact

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

    The neuron detects prominent document headings or title-like, strongly emphasized section starts (formatted/large tokens that introduce a new topic).

    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
    蘞
    0.40
     indicating
    0.40
     realizan
    0.40
     groups
    0.39
     based
    0.39
     using
    0.38
     similar
    0.38
    女性
    0.38
     usages
    0.38
     linestyle
    0.38
    POSITIVE LOGITS
     😉
    0.65
     glorie
    0.65
     glorious
    0.63
     extravaganza
    0.63
     delicioso
    0.63
     pesky
    0.60
     :).
    0.60
     gemüt
    0.60
     ;-)
    0.59
     😎
    0.57
    Activations Density 0.330%

    No Known Activations