© 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. 239438
    Prev
    Next
    INDEX
    Explanations

    physical inspection

    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
     և
    0.49
    ']);
    0.49
     and
    0.47
    peł
    0.47
     aye
    0.46
     ज
    0.46
    peak
    0.45
     san
    0.45
     ಅಂತ
    0.44
     go
    0.44
    POSITIVE LOGITS
    мун
    0.46
    옥
    0.45
    问题
    0.44
    ຜະລິດຕະພັນ
    0.44
    奀
    0.44
    например
    0.44
    ซึ่ง
    0.43
    ლები
    0.43
    牍
    0.42
     типу
    0.41
    Activations Density 0.001%

    No Known Activations