© 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. 173022
    Prev
    Next
    INDEX
    Explanations

    kegs and cookies

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

    combination square, IQ tests, MTSamples, manipulating data, residence time

    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
    шча
    0.54
    epoca
    0.51
     misconceptions
    0.47
     NOV
    0.47
    জয়
    0.45
    твы
    0.45
    제
    0.45
    ოლ
    0.44
     NOR
    0.44
    छोटी
    0.44
    POSITIVE LOGITS
     শ্ব
    0.47
     रोजिक
    0.47
     клиент
    0.47
     kişiler
    0.46
     व्यक्तियों
    0.44
     হবি
    0.44
     umfass
    0.44
     كلهم
    0.43
     включа
    0.42
     hydrating
    0.42
    Activations Density 0.000%

    No Known Activations