© 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. 82219
    Prev
    Next
    INDEX
    Explanations

    you're right to be

    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
    ուն
    0.43
     cent
    0.42
     pesar
    0.41
    貸款
    0.41
    &
    0.39
     கடந்த
    0.38
     ಸೆ
    0.37
     décoration
    0.37
     собственного
    0.37
     التد
    0.37
    POSITIVE LOGITS
    🧛
    0.47
    🧙
    0.45
    🧟
    0.44
    假设
    0.43
     whereupon
    0.43
     asynchronously
    0.42
    रविवार
    0.42
    '",
    0.42
    DIN
    0.42
     Boundaries
    0.41
    Activations Density 0.006%

    No Known Activations