© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19934
    Prev
    Next
    INDEX
    Explanations

    negation and absence

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

    class goesactivities takeconnection betweenrelated keywordssharing experiencesno thanksthe song

    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
     коль
    0.43
    込んで
    0.41
     じゃ
    0.41
    ﻔ
    0.41
     מב
    0.40
    捍
    0.40
    <0x80>
    0.40
    銛
    0.39
    꽈
    0.39
     judge
    0.38
    POSITIVE LOGITS
    is
    0.50
     ಹಲವಾರು
    0.49
    are
    0.49
    क्यूमेंट
    0.48
     একাধিক
    0.48
     undertook
    0.47
    tStart
    0.47
    have
    0.45
     الشركات
    0.45
     produk
    0.45
    Activations Density 0.000%

    No Known Activations