© 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. 204963
    Prev
    Next
    INDEX
    Explanations

    explaining concepts or documents

    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
    堅持
    0.43
     elution
    0.42
    銨
    0.42
     vecinos
    0.42
     России
    0.42
    겠지만
    0.41
     পারবে
    0.41
     tradiz
    0.41
    ابت
    0.41
    诿
    0.40
    POSITIVE LOGITS
    sko
    0.47
    ни
    0.47
    MM
    0.46
    osx
    0.45
    ntgen
    0.44
    Z
    0.44
    ისი
    0.44
    vis
    0.44
    oughby
    0.44
    য়াছে
    0.43
    Activations Density 0.005%

    No Known Activations