© 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. 234891
    Prev
    Next
    INDEX
    Explanations

    provide a

    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
     assessment
    0.41
    Tres
    0.41
    teur
    0.40
    Ala
    0.39
    luft
    0.39
    脫
    0.39
    lied
    0.39
    thorne
    0.39
     видели
    0.39
    愧
    0.39
    POSITIVE LOGITS
     zakoń
    0.55
     disposiciones
    0.54
     根据
    0.49
     લ
    0.48
    েমনি
    0.48
    ﻡ
    0.48
     formie
    0.48
     okresie
    0.46
    icznych
    0.46
     końca
    0.46
    Activations Density 0.001%

    No Known Activations