© 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. 111504
    Prev
    Next
    INDEX
    Explanations

    capacity gauge

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

    multiple fully copies

    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
     معنا
    0.47
    看向
    0.45
     वॉ
    0.44
    परे
    0.43
     Dickinson
    0.43
    媺
    0.43
    IKO
    0.42
    哭了
    0.42
     빅뱅
    0.41
    ैया
    0.41
    POSITIVE LOGITS
    coupled
    0.47
    ０
    0.47
    ľov
    0.45
     netto
    0.45
    brought
    0.45
     czł
    0.44
    ០
    0.43
    inuous
    0.43
     prost
    0.43
    continuous
    0.43
    Activations Density 0.001%

    No Known Activations