© 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. 105463
    Prev
    Next
    INDEX
    Explanations

    requirements, appraisal, table

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

    Renaissance Masters and Titans

    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
    ጦ
    0.47
    ським
    0.47
    م
    0.47
    目で
    0.46
    িশ
    0.45
    قرار
    0.45
     lossless
    0.44
    шою
    0.44
    pias
    0.43
    ртом
    0.43
    POSITIVE LOGITS
     lir
    0.49
     雨
    0.46
    的其他
    0.46
     保
    0.45
     parseInt
    0.45
     trebui
    0.44
     caught
    0.44
     Wexford
    0.43
     lov
    0.43
     GU
    0.43
    Activations Density 0.000%

    No Known Activations