© 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. 195213
    Prev
    Next
    INDEX
    Explanations

    operation planning

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

    purpose is, true

    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
     നേതാ
    0.50
    علوم
    0.46
     ۱۵
    0.46
    钬
    0.45
     فوتبال
    0.45
     Comprehensive
    0.44
     ବି
    0.43
    お店
    0.43
     indiquant
    0.43
     Sciences
    0.43
    POSITIVE LOGITS
     accidental
    0.54
     liber
    0.53
     verdadera
    0.52
     efet
    0.50
    自己
    0.50
     reste
    0.50
     da
    0.49
    可
    0.49
    地
    0.48
     come
    0.47
    Activations Density 0.002%

    No Known Activations