© 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. 98396
    Prev
    Next
    INDEX
    Explanations

    trees, sale, amplifier, rust

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

    date or talking about decisions

    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
     fiestas
    0.44
    leşik
    0.43
     ファッション
    0.42
     raggi
    0.41
     Более
    0.41
     вікі
    0.40
     geologist
    0.40
     კ
    0.40
     קי
    0.40
     temprano
    0.40
    POSITIVE LOGITS
    ::-
    0.45
    該
    0.45
    ,\
    0.44
    ᆻ
    0.44
    +\
    0.43
    ,((
    0.43
    菣
    0.43
    這種
    0.43
    nit
    0.42
    接口
    0.42
    Activations Density 0.000%

    No Known Activations