© 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. 160380
    Prev
    Next
    INDEX
    Explanations

    publication dates and authors

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

    diverse languages and subjects

    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
    nite
    0.44
    >(
    0.42
    ated
    0.42
    ＼
    0.42
     สาม
    0.41
    ीन
    0.40
    輻
    0.40
    operators
    0.39
    彿
    0.39
    \&
    0.38
    POSITIVE LOGITS
     eleições
    0.55
    ﻱ
    0.53
     cortar
    0.52
     GridLayout
    0.50
     sıv
    0.49
     Олег
    0.48
    ্যাস
    0.48
    ECs
    0.48
     Heel
    0.47
     salir
    0.47
    Activations Density 0.001%

    No Known Activations