© 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. 51631
    Prev
    Next
    INDEX
    Explanations

    links, permalink, house, page, certificate

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

    block his number

    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
     highway
    0.51
     Ο
    0.49
     त्यो
    0.45
    ти
    0.44
     terang
    0.43
    ainkan
    0.43
     ईस्ट
    0.43
    entingan
    0.43
     enmity
    0.43
    ȟ
    0.42
    POSITIVE LOGITS
    梦
    0.44
     rév
    0.43
     Sorting
    0.43
     NSUInteger
    0.42
     Gage
    0.42
     Attached
    0.42
    码
    0.42
    绩
    0.41
    百分
    0.41
     Multivariate
    0.41
    Activations Density 0.000%

    No Known Activations