© 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. 253156
    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
    こんにちは
    0.43
    -=
    0.41
    representing
    0.41
    хан
    0.40
     mechanized
    0.39
    absence
    0.39
    örm
    0.39
    seid
    0.39
    یک
    0.38
    یکی
    0.38
    POSITIVE LOGITS
    ﻙ
    0.44
     SOURCES
    0.41
     আস
    0.40
    LENGTH
    0.40
     raha
    0.40
     candidats
    0.40
    IE
    0.39
     periphery
    0.39
     れる
    0.39
     বলছেন
    0.39
    Activations Density 0.005%

    No Known Activations