© 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. 191762
    Prev
    Next
    INDEX
    Explanations

    from the moment we

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

    shock, amplifier configurations, state between

    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
     Terbaik
    0.49
    खनऊ
    0.49
     Firmware
    0.49
     базу
    0.48
    값을
    0.48
     ಯಾ
    0.47
    \":
    0.47
     รถ
    0.47
     Automobile
    0.46
    کسی
    0.46
    POSITIVE LOGITS
     guilds
    0.53
     hospitals
    0.51
    রণে
    0.49
     asteroids
    0.49
     orbits
    0.48
     anhyd
    0.48
     choirs
    0.48
     apoi
    0.47
     anchorage
    0.46
     nurseries
    0.46
    Activations Density 0.001%

    No Known Activations