© 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. 131898
    Prev
    Next
    INDEX
    Explanations

    bank partners classes water occasion

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

    Shinjuku Gyoen National Garden

    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
    삑
    0.49
    Installed
    0.49
    scrollTop
    0.46
    本社
    0.46
    ب
    0.46
    आप
    0.45
     Installed
    0.45
    ($('#
    0.44
    뺨
    0.44
    сто
    0.44
    POSITIVE LOGITS
    ur
    0.55
     mines
    0.55
     valu
    0.51
     produc
    0.50
     দা
    0.48
     d
    0.47
    zeros
    0.47
     lat
    0.46
    cket
    0.46
    veland
    0.46
    Activations Density 0.000%

    No Known Activations