© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 138001
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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_16_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
    T
    1.52
    P
    1.30
    H
    1.28
    S
    1.23
    L
    1.03
    AN
    1.02
    B
    1.02
    y
    1.00
    K
    1.00
    Т
    0.96
    POSITIVE LOGITS
    д
    1.92
    ",
    1.78
    as
    1.66
    د
    1.57
    ש
    1.56
    are
    1.51
    л
    1.42
    ோ
    1.41
    ',
    1.39
    ä
    1.36
    Activations Density 0.101%

    No Known Activations