© 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. 234761
    Prev
    Next
    INDEX
    Explanations

    virology, parasitology, strength, crash, four doctors, back to Boston, La Boca

    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
     فوتب
    0.47
     sportif
    0.47
     sanguin
    0.46
    nath
    0.45
    🇶
    0.44
    ्यू
    0.44
     بیل
    0.43
     titres
    0.43
     Partai
    0.43
     Парт
    0.43
    POSITIVE LOGITS
    生效
    0.51
    आज
    0.50
    GOING
    0.50
    에요
    0.47
    MASS
    0.46
     IT
    0.45
    तो
    0.45
    a
    0.45
    Down
    0.44
    Tul
    0.44
    Activations Density 0.000%

    No Known Activations