© 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. 29694
    Prev
    Next
    INDEX
    Explanations

    is home to, are lots of

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

    outlier detection

    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
    an
    0.52
     explic
    0.44
    鵡
    0.43
     soundtrack
    0.41
    Simply
    0.41
     unravel
    0.41
    لن
    0.41
     當
    0.41
    開幕
    0.41
    나
    0.41
    POSITIVE LOGITS
     ocasión
    0.49
    cgColor
    0.47
    ión
    0.46
     incênd
    0.45
     Cô
    0.44
     TAB
    0.43
     কোভিড
    0.43
    evt
    0.43
    úd
    0.43
     nhiễm
    0.43
    Activations Density 0.000%

    No Known Activations