© 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. 90577
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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/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
    4
    0.46
     Kar
    0.42
    5
    0.40
    ツール
    0.39
    8
    0.39
    6
    0.39
    IB
    0.39
     Br
    0.37
    ஆர்
    0.37
     kar
    0.37
    POSITIVE LOGITS
    endsWith
    0.41
     opposites
    0.40
     კიდ
    0.40
     "."
    0.39
    held
    0.38
    lowing
    0.38
     uniqueness
    0.38
     "_"
    0.38
     participle
    0.38
    oxine
    0.38
    Activations Density 0.008%

    No Known Activations