© 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. 256682
    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
    នៅលើ
    0.42
     Tired
    0.41
    ین
    0.41
    ၌
    0.40
    用的
    0.40
     বিজয়
    0.40
    说的
    0.39
    Wonderful
    0.39
     Salsa
    0.39
     ভাবনা
    0.39
    POSITIVE LOGITS
     повіт
    0.47
     ausreiche
    0.46
    系数
    0.46
     或
    0.45
    jsce
    0.44
     základ
    0.43
    𝓙
    0.43
     ㄱ
    0.42
     $<
    0.42
     系
    0.42
    Activations Density 0.000%

    No Known Activations