© 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. 33924
    Prev
    Next
    INDEX
    Explanations

    punctuation and delimiters

    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
    @]
    0.49
     &:
    0.44
     lasagna
    0.43
     &.
    0.43
     aten
    0.43
     comerciais
    0.42
     amp
    0.42
    饅
    0.42
     atrop
    0.41
     అన
    0.41
    POSITIVE LOGITS
     punctuation
    1.41
     delimiters
    1.33
     delimiter
    1.31
    punctuation
    1.24
    Delimiter
    1.23
    delimiter
    1.20
     delim
    1.08
     delimit
    1.05
     punctu
    1.05
    delim
    1.04
    Activations Density 0.005%

    No Known Activations