© 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. 41-GEMMASCOPE-2-RES-262K
    7. 98895
    Prev
    Next
    INDEX
    Explanations

    delimiter or separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     punctuation
    0.54
     parenthesis
    0.45
     punctuated
    0.44
     suscrib
    0.43
     parentheses
    0.43
     Pun
    0.43
     commas
    0.43
    陈
    0.43
     paréntesis
    0.41
     Pari
    0.39
    POSITIVE LOGITS
     separator
    0.63
     separators
    0.63
    separator
    0.60
     delimiter
    0.59
     separations
    0.52
    delimiter
    0.52
     separating
    0.51
     指定
    0.49
     použí
    0.49
     kriter
    0.46
    Activations Density 0.001%

    No Known Activations