© 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. 145044
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to

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

    greater than or equal to version

    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
    دين
    0.50
    悰
    0.49
    nicht
    0.49
     শিক্ষার্থীরা
    0.47
    ಟ
    0.47
    ্রেক
    0.46
    िरपेक्ष
    0.44
    কেউ
    0.44
    鬢
    0.44
     மாணவர்கள்
    0.44
    POSITIVE LOGITS
    the
    0.50
    ;
    0.50
    The
    0.49
    h
    0.46
    llll
    0.45
    ,
    0.45
     The
    0.44
     ,
    0.43
    ;,
    0.43
     Counts
    0.43
    Activations Density 0.000%

    No Known Activations