© 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. 150620
    Prev
    Next
    INDEX
    Explanations

    deposit or quantity

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

    native datasets consistently outperform

    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
     pessoais
    0.49
     Лондон
    0.45
     多く
    0.43
    瞞
    0.43
     nied
    0.42
     Londra
    0.42
     Bobcats
    0.42
     docks
    0.41
     millioner
    0.41
     circus
    0.41
    POSITIVE LOGITS
    Chill
    0.49
    Native
    0.49
    iculo
    0.47
     of
    0.47
    Nested
    0.45
     نصف
    0.44
    žio
    0.44
    ibernate
    0.44
    心
    0.44
    Heart
    0.44
    Activations Density 0.001%

    No Known Activations