© 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. 131404
    Prev
    Next
    INDEX
    Explanations

    considered complete

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

    limits and calculations

    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
    લ
    0.52
     willow
    0.49
     کافی
    0.46
     offerte
    0.45
    ស្ថាន
    0.45
    事例
    0.45
    ન
    0.45
     ઉપયોગ
    0.44
     સિ
    0.44
     સી
    0.44
    POSITIVE LOGITS
    🌓
    0.51
    層
    0.50
     Majorana
    0.50
    idazol
    0.49
     Buyer
    0.49
     Banker
    0.47
     proficiency
    0.47
     Sellers
    0.46
     Heterocycl
    0.46
     Catholicism
    0.46
    Activations Density 0.000%

    No Known Activations