© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65926
    Prev
    Next
    INDEX
    Explanations

    dealt with or prevents

    np_acts-logits-general · gemini-2.5-flash-lite

    works and not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     이번
    0.52
    та
    0.51
    𝘫
    0.51
    폼
    0.50
    𝘸
    0.50
     পয়েন্ট
    0.49
    最初に
    0.48
    裟
    0.48
     сбор
    0.48
    ༥
    0.48
    POSITIVE LOGITS
    in
    0.53
    在新
    0.40
     Holmes
    0.39
    an
    0.39
     conserv
    0.39
    BuildConfig
    0.39
    もら
    0.39
     Betty
    0.38
    chis
    0.38
    ·
    0.38
    Activations Density 0.000%

    No Known Activations