© 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. 80926
    Prev
    Next
    INDEX
    Explanations

    supports or reduction

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

    Indigenous Peoples/Roots

    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
    h
    0.57
     h
    0.50
     小型
    0.44
     Planck
    0.44
     Whitehall
    0.44
     sensitive
    0.43
    applications
    0.43
     Applications
    0.42
     Finite
    0.42
     Sure
    0.42
    POSITIVE LOGITS
     namik
    0.59
    kowych
    0.54
    কা
    0.52
    িন্দা
    0.51
     REGIUNI
    0.51
     updateConfirm
    0.51
    Ⴚ
    0.50
    못
    0.50
    ヤモンド
    0.49
    榊
    0.49
    Activations Density 0.000%

    No Known Activations