© 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. 210917
    Prev
    Next
    INDEX
    Explanations

    what is

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

    diverse concepts and foreign words

    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
    0.51
    FON
    0.49
    慳
    0.48
    WON
    0.46
    QU
    0.46
    WAS
    0.45
     लगना
    0.45
    EIN
    0.44
    TAP
    0.43
    DN
    0.42
    POSITIVE LOGITS
     آسیب
    0.49
    的声音
    0.47
    نې
    0.45
    టర్‌
    0.45
    އ
    0.45
    pointB
    0.44
     multiSelectList
    0.44
    šao
    0.44
     வாக்கு
    0.43
     griev
    0.43
    Activations Density 0.001%

    No Known Activations