© 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. 105820
    Prev
    Next
    INDEX
    Explanations

    stainless steel and numbers

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

    instructions, commands, history

    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
     мероприятия
    0.50
    лық
    0.50
    兕
    0.49
    鉭
    0.49
    部件
    0.48
    вни
    0.47
    град
    0.47
    ὤ
    0.46
     범위
    0.46
    жнему
    0.46
    POSITIVE LOGITS
     Context
    0.52
     Hong
    0.50
     Japanese
    0.49
     World
    0.48
     or
    0.47
     Toronto
    0.47
     Communist
    0.46
     U
    0.46
     Soviet
    0.46
     Dopo
    0.46
    Activations Density 0.001%

    No Known Activations