© 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. 107591
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    evaluations and conditions

    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
     ತೆಗೆದುಕೊಳ್ಳ
    0.47
    jima
    0.45
    {
    0.45
    𝙞
    0.43
    is
    0.43
     चिल्ड्रन
    0.43
    Children
    0.43
    of
    0.43
    ate
    0.42
    be
    0.42
    POSITIVE LOGITS
    تباط
    0.49
     oznacza
    0.47
     देणे
    0.47
    پرس
    0.46
    倚
    0.46
     informace
    0.46
     informiert
    0.46
     ponú
    0.46
    اعری
    0.46
    정한
    0.46
    Activations Density 0.000%

    No Known Activations