© 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. 25415
    Prev
    Next
    INDEX
    Explanations

    payment plan discretion book range

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

    story continuation

    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
    ‏
    0.45
    been
    0.45
     Seg
    0.45
    हद
    0.45
    :@
    0.44
     меж
    0.44
    情节
    0.43
    seg
    0.43
    тых
    0.43
     э
    0.42
    POSITIVE LOGITS
    PLICATION
    0.50
    明る
    0.48
    RO
    0.47
    াহিনী
    0.47
    UTONIUM
    0.46
     voltages
    0.45
    原理
    0.45
    정과
    0.45
     sizes
    0.44
    CTS
    0.43
    Activations Density 0.000%

    No Known Activations