© 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. 109427
    Prev
    Next
    INDEX
    Explanations

    names and people

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

    lists and enumerated items

    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
     ujian
    0.57
     sınav
    0.57
     dificultades
    0.56
    朊
    0.56
     kesulitan
    0.55
    BUGFS
    0.54
     adsor
    0.54
     اختبار
    0.53
     oblik
    0.52
     exámenes
    0.52
    POSITIVE LOGITS
    еш
    0.52
    Union
    0.52
    one
    0.51
    )'
    0.50
    Gary
    0.49
    FirstName
    0.49
    2
    0.48
    Philippe
    0.47
    Way
    0.47
    Name
    0.47
    Activations Density 0.000%

    No Known Activations