© 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. 41787
    Prev
    Next
    INDEX
    Explanations

    task creation AI

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

    the neuron detects section headings or emphasized technical/title tokens (tokens that appear in headers, bolded/important terms, or list/section titles).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    ాల
    0.50
    ﹍
    0.49
     Forget
    0.49
    ებმა
    0.45
    人形
    0.44
     Here
    0.44
     Pier
    0.44
     ServiceNow
    0.44
    无人
    0.43
     Regardless
    0.43
    POSITIVE LOGITS
    OR
    0.57
    i
    0.50
    GAM
    0.48
    n
    0.47
    IRD
    0.46
    iD
    0.46
    ORIA
    0.45
    Lors
    0.45
    Cu
    0.44
    अग
    0.43
    Activations Density 0.000%

    No Known Activations