© 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. 256839
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Nasir
    0.54
    そもそも
    0.49
     Nas
    0.47
     أق
    0.47
    ﻜ
    0.47
    の中でも
    0.46
     Nuestros
    0.45
    קה
    0.45
     Maison
    0.44
    ٍ
    0.44
    POSITIVE LOGITS
    𝚅
    0.47
    on
    0.46
    லிக்க
    0.46
    烁
    0.45
     favourites
    0.45
    ତ୍
    0.44
    onen
    0.44
     εξε
    0.44
    favourites
    0.44
    won
    0.43
    Activations Density 0.001%

    No Known Activations