© 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. 128130
    Prev
    Next
    INDEX
    Explanations

    various kinds of

    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
    ច្រ
    0.47
    坳
    0.47
    ність
    0.46
    ೇಶ
    0.45
    paced
    0.43
    ника
    0.42
    ベーション
    0.41
    ンテ
    0.41
     صالح
    0.39
    чности
    0.39
    POSITIVE LOGITS
    各种
    0.55
     Sleeping
    0.52
    씩
    0.52
     each
    0.51
     perfume
    0.51
     similar
    0.50
    类似
    0.50
     Immune
    0.50
     adet
    0.49
    ல்லாம்
    0.49
    Activations Density 0.007%

    No Known Activations