© 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-16K
    7. 6067
    Prev
    Next
    INDEX
    Explanations

    redirection operators or 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/layer_31_width_16k_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
    ：
    0.62
    <?=
    0.58
    ”،
    0.57
    ни
    0.57
    that
    0.55
    Governor
    0.54
     ممكن
    0.53
    GH
    0.52
    ARE
    0.52
    Apellido
    0.51
    POSITIVE LOGITS
    ிற
    0.62
    I
    0.61
    iid
    0.61
     julg
    0.58
    ik
    0.57
    os
    0.56
    ද්ධ
    0.56
     grayscale
    0.55
    一个小
    0.54
    iq
    0.54
    Activations Density 0.069%

    No Known Activations