© 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. 13750
    Prev
    Next
    INDEX
    Explanations

    are amusing

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

    binary, shape, markers

    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
     बेचने
    0.57
    রন
    0.55
    PropertyParam
    0.53
    '){
    0.52
     アイアン
    0.51
    washer
    0.51
    '?
    0.50
    ClearedBy
    0.50
    '.
    0.49
     Avenger
    0.49
    POSITIVE LOGITS
    ني
    0.52
    ﻒ
    0.52
    讓我
    0.49
    𝟘
    0.49
    ﻔ
    0.49
     xii
    0.49
    exerc
    0.48
     converge
    0.47
     tradiz
    0.47
     janela
    0.46
    Activations Density 0.000%

    No Known Activations