© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203803
    Prev
    Next
    INDEX
    Explanations

    modify and repair data

    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
     ню
    0.42
    動き
    0.41
    出して
    0.41
     Kick
    0.41
    躾
    0.41
    鳎
    0.40
     आणि
    0.40
    лга
    0.40
     dzien
    0.39
    乨
    0.39
    POSITIVE LOGITS
    t
    0.61
    r
    0.59
    l
    0.54
    ت
    0.53
    T
    0.50
    تي
    0.48
    g
    0.47
    LEY
    0.47
    TRO
    0.47
    H
    0.46
    Activations Density 0.005%

    No Known Activations