© 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. 86395
    Prev
    Next
    INDEX
    Explanations

    paid amounts semester tributaries practice

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

    muscles squeeze

    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
     ouvre
    0.55
    ما
    0.49
    ре
    0.48
    نا
    0.47
    िव
    0.47
    س
    0.46
    ن
    0.46
    st
    0.43
    চ
    0.43
    ﻛ
    0.43
    POSITIVE LOGITS
    asciiPanel
    0.55
     শ্রেণীর
    0.52
     उस
    0.50
     USING
    0.50
     পরিশ
    0.50
     باستخدام
    0.49
     फाइबर
    0.49
     علاقوں
    0.49
     этими
    0.49
     பயன்படுத்தி
    0.48
    Activations Density 0.000%

    No Known Activations