© 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. 7961
    Prev
    Next
    INDEX
    Explanations

    URLs containing slashes and hyphens

    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
     मेकअप
    0.35
     اتھار
    0.35
     édition
    0.34
    潴
    0.34
    👛
    0.34
     업데이트
    0.33
     ሽፋን
    0.33
     देयर
    0.33
    ⬮
    0.32
     ؟
    0.32
    POSITIVE LOGITS
    0.36
    un
    0.35
    -
    0.34
     t
    0.33
    i
    0.33
    s
    0.32
    1
    0.32
    t
    0.32
    r
    0.32
    l
    0.31
    Activations Density 0.004%

    No Known Activations