© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81472
    Prev
    Next
    INDEX
    Explanations

    finish ages

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

    values, access, might, being, note

    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
    i
    0.48
    !
    0.46
    uron
    0.44
    gı
    0.43
    uza
    0.41
    ి
    0.41
     persec
    0.40
     xét
    0.40
     facies
    0.39
     khởi
    0.39
    POSITIVE LOGITS
    Shares
    0.52
     निखिल
    0.50
     Squadron
    0.49
    CompanyName
    0.49
    管理
    0.47
     clube
    0.47
     Еў
    0.46
     IntPtr
    0.46
    强化
    0.46
    Ⲣ
    0.46
    Activations Density 0.001%

    No Known Activations