© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1973
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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_40_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
     implicitly
    0.38
     !
    0.35
    ر
    0.34
     indeed
    0.33
     sort
    0.32
     अथवा
    0.31
     something
    0.31
    可以说
    0.31
    {
    0.31
    或其他
    0.30
    POSITIVE LOGITS
     that
    0.45
    that
    0.42
     bahawa
    0.41
     bahwa
    0.39
     що
    0.36
     ότι
    0.36
     что
    0.34
    𝘞
    0.34
     że
    0.33
    ："
    0.33
    Activations Density 0.003%

    No Known Activations