© 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. 201402
    Prev
    Next
    INDEX
    Explanations

    as anof instantDrag Reductionplasma confinement

    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
    ग
    0.45
    덥
    0.43
     pumps
    0.43
    CurrentUser
    0.42
    P
    0.42
    Priv
    0.41
    ATIONAL
    0.41
    Weak
    0.41
    vived
    0.41
    TabLayout
    0.41
    POSITIVE LOGITS
     숫자
    0.49
    ną
    0.46
     Seç
    0.45
    െന്നാണ്
    0.45
     Déc
    0.44
     Mục
    0.44
    珞
    0.44
    urgie
    0.43
    zić
    0.42
     Arten
    0.42
    Activations Density 0.002%

    No Known Activations