© 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. 109884
    Prev
    Next
    INDEX
    Explanations

    why things happen

    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
    )}+\
    0.47
    Укупно
    0.46
    류
    0.46
    explore
    0.45
    abile
    0.44
    flexible
    0.44
    Life
    0.43
    Liter
    0.42
    evice
    0.42
    elines
    0.42
    POSITIVE LOGITS
    c
    0.54
    中は
    0.52
     Mohawk
    0.49
     intersecting
    0.47
     interrupted
    0.47
     иг
    0.46
     alf
    0.45
     interruption
    0.43
     interment
    0.43
     fenced
    0.43
    Activations Density 0.006%

    No Known Activations