© 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. 8046
    Prev
    Next
    INDEX
    Explanations

    description:

    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
     beheld
    0.41
     irradiation
    0.40
     했다
    0.39
     था
    0.38
     rhy
    0.38
     яким
    0.38
    ។
    0.38
     сви
    0.38
     Бүген
    0.37
     TextStyle
    0.37
    POSITIVE LOGITS
    at
    0.58
    സ
    0.44
    is
    0.43
    ס
    0.43
    ق
    0.43
    atched
    0.43
    ió
    0.42
    el
    0.40
    as
    0.40
    io
    0.40
    Activations Density 0.013%

    No Known Activations