© 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. 122642
    Prev
    Next
    INDEX
    Explanations

    code block structures

    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
    ;;
    0.40
     ").
    0.40
    grades
    0.39
    stencil
    0.39
    followed
    0.39
     를
    0.38
    `).
    0.38
    rbrack
    0.38
     Австра
    0.38
    rollerskates
    0.37
    POSITIVE LOGITS
     mislead
    0.48
     Unido
    0.44
    χαν
    0.43
     quia
    0.43
     মূ
    0.43
    玮
    0.42
     wielu
    0.42
     misguided
    0.42
     calme
    0.41
    ﻌ
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.