© 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. 76854
    Prev
    Next
    INDEX
    Explanations

    statistical analysis

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

    defining words in contexts

    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
    曾經
    0.47
    ন্‌
    0.46
     Фі
    0.46
     pandémie
    0.46
    粝
    0.45
    decomposition
    0.45
     особенностей
    0.45
     форм
    0.45
     সর্বাধিক
    0.45
    ப்படாத
    0.45
    POSITIVE LOGITS
    p
    0.60
    ’
    0.48
    r
    0.44
    λ
    0.43
    은
    0.41
    b
    0.41
    less
    0.41
     mimic
    0.41
    an
    0.40
    akra
    0.40
    Activations Density 0.001%

    No Known Activations