© 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. 121535
    Prev
    Next
    INDEX
    Explanations

    London, acute injury, smartphone, largest

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

    phishing, abuse, founder, Boca, erased, however

    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
    a
    0.56
    aughan
    0.53
    o
    0.50
    ̔
    0.46
    iors
    0.45
    噌
    0.44
    eers
    0.44
    eds
    0.43
    دو
    0.43
    Counts
    0.43
    POSITIVE LOGITS
     পরিবহ
    0.45
     tradeoff
    0.45
    捩
    0.44
    螞
    0.44
     യു
    0.43
     çek
    0.43
     mouvement
    0.43
     プリント
    0.42
     ブリヂストン
    0.41
     movimiento
    0.41
    Activations Density 0.000%

    No Known Activations