© 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. 210806
    Prev
    Next
    INDEX
    Explanations

    prettyface Mia

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

    historical precedents or underlying functions

    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
    ”
    0.48
    ()
    0.46
     הת
    0.44
     הא
    0.44
    t
    0.43
    i
    0.42
    רי
    0.42
     sobie
    0.42
    听到
    0.42
    pert
    0.42
    POSITIVE LOGITS
    棪
    0.47
     Pawar
    0.47
     অনুসারে
    0.44
     rougeâtres
    0.43
     দেখুনঃ
    0.42
    骠
    0.42
     accords
    0.42
    রা
    0.42
     mediators
    0.41
     সুন্দরী
    0.41
    Activations Density 0.000%

    No Known Activations