© 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. 17419
    Prev
    Next
    INDEX
    Explanations

    drawing or reaching for items

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

    reach into containers

    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
    监听页面
    0.44
     juillet
    0.43
     hôtel
    0.42
     mesaj
    0.42
    boomerang
    0.42
     météor
    0.41
    ..--..--
    0.41
     crédito
    0.40
    hear
    0.40
    Chevron
    0.40
    POSITIVE LOGITS
    섞
    0.55
     balls
    0.53
    混ぜ
    0.52
    放入
    0.52
     gloves
    0.50
     뽑
    0.50
     गेंदों
    0.47
    抽出
    0.46
     blindly
    0.46
     mixing
    0.46
    Activations Density 0.027%

    No Known Activations