© 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. 209213
    Prev
    Next
    INDEX
    Explanations

    patients who, advocate, will be

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

    Caribbean pirate

    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
    мов
    0.59
     usato
    0.54
    Фі
    0.53
    Посилання
    0.50
    次数
    0.50
     uncl
    0.50
    약
    0.50
    провод
    0.49
    гія
    0.48
     astral
    0.48
    POSITIVE LOGITS
    era
    0.50
     Xinhua
    0.47
    erc
    0.47
     Mc
    0.47
     Ç
    0.46
     Pt
    0.46
    KH
    0.46
    textup
    0.44
     CHAM
    0.44
     KH
    0.44
    Activations Density 0.000%

    No Known Activations