© 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. 34568
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
    隧
    0.49
     अगर
    0.44
     ਗਈ
    0.44
     თუ
    0.43
     ако
    0.43
    geg
    0.43
     اسم
    0.43
    ኞ
    0.42
    であるが
    0.41
    ifaiFace
    0.41
    POSITIVE LOGITS
    概述
    0.55
    Introduction
    0.50
    Reason
    0.46
    combined
    0.46
    Posted
    0.45
     ISSUE
    0.45
    Description
    0.45
    합니다
    0.44
     exuberant
    0.44
    Code
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.