© 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. 39342
    Prev
    Next
    INDEX
    Explanations

    UTC timestamp markers

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

    keywords and their context

    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
    fe
    0.54
    seq
    0.54
    shot
    0.54
    u
    0.53
    ob
    0.52
    im
    0.52
    shots
    0.52
     I
    0.52
    ui
    0.52
    fl
    0.51
    POSITIVE LOGITS
    哞
    0.50
     수를
    0.48
     échanc
    0.47
     légumes
    0.46
     কাকে
    0.46
     myof
    0.46
     ponctuées
    0.45
     consecut
    0.45
    溺
    0.45
     quelqu
    0.45
    Activations Density 0.000%

    No Known Activations