© 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. 52900
    Prev
    Next
    INDEX
    Explanations

    photo, angle, spot, guitar

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

    technical terms and their definitions

    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
    ви
    0.52
     inici
    0.51
    et
    0.49
     and
    0.47
     focal
    0.47
     of
    0.46
    ט
    0.46
     founded
    0.46
    res
    0.45
     vrch
    0.45
    POSITIVE LOGITS
     ရက်
    0.54
    यॉर्क
    0.54
     ಹಾಸ
    0.54
     Grub
    0.52
     ጡ
    0.52
     いや
    0.49
     優
    0.48
     カラー
    0.48
    ⓜ
    0.47
     フランス
    0.47
    Activations Density 0.000%

    No Known Activations