© 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. 210058
    Prev
    Next
    INDEX
    Explanations

    anesthesiologist, plasmatologist, radiologist

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

    when to use

    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
     эле
    0.54
    驛
    0.52
     Urlaub
    0.52
     Czę
    0.51
    তনে
    0.50
     Africans
    0.49
     여행
    0.49
     образу
    0.46
     건축
    0.46
    🛖
    0.46
    POSITIVE LOGITS
     Minaj
    0.50
    antiates
    0.46
    ologische
    0.46
    fler
    0.44
     gearbox
    0.44
    ayon
    0.43
    estock
    0.43
     stockpile
    0.42
    ull
    0.42
     Nato
    0.42
    Activations Density 0.000%

    No Known Activations