© 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. 252637
    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
    <0xBE>
    0.49
    laublich
    0.48
     वकील
    0.48
    rekken
    0.47
    ურთიერთ
    0.47
    lä
    0.47
    fonos
    0.47
    apadani
    0.47
    ಿಸಿಕೊಳ್ಳ
    0.46
    ěn
    0.46
    POSITIVE LOGITS
    TI
    0.58
    omit
    0.52
     Egi
    0.50
    c
    0.49
     eng
    0.46
     omit
    0.46
     Área
    0.45
     Aqu
    0.45
    en
    0.44
    Qu
    0.44
    Activations Density 0.001%

    No Known Activations