© 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. 20918
    Prev
    Next
    INDEX
    Explanations

    speed, height, health

    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
     M
    0.46
    。
    0.42
    '
    0.38
     zuvor
    0.38
     ۱۳۹
    0.38
    接待
    0.37
     bloodstream
    0.36
    kken
    0.35
     Gastgeber
    0.35
     Ethernet
    0.35
    POSITIVE LOGITS
    刓
    0.53
    OfString
    0.49
     വർ
    0.47
    慗
    0.45
    這些
    0.45
    癃
    0.44
     വര്‍
    0.43
     Danach
    0.43
    fourths
    0.42
    applique
    0.42
    Activations Density 0.001%

    No Known Activations