© 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. 244754
    Prev
    Next
    INDEX
    Explanations

    in words like Braun or section

    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
    ﻓ
    0.49
    লেখা
    0.48
    어를
    0.48
     หา
    0.48
    śla
    0.48
    S
    0.48
     결혼
    0.46
    ра
    0.46
    plein
    0.46
     kama
    0.46
    POSITIVE LOGITS
     Respondents
    0.47
     cotid
    0.46
     Immutable
    0.46
     διαδικ
    0.46
     것은
    0.43
     ē
    0.43
     ஜனநாயக
    0.43
     infrastrukt
    0.43
     Conversely
    0.43
    igueur
    0.42
    Activations Density 0.000%

    No Known Activations