© 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. 159109
    Prev
    Next
    INDEX
    Explanations

    festival session, app, Theatre, information

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

    connected, offline, value

    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
    for
    0.63
     for
    0.53
    fib
    0.47
    if
    0.47
    ware
    0.47
    ↵
    0.46
     Sine
    0.46
    umu
    0.45
    print
    0.45
    lr
    0.45
    POSITIVE LOGITS
    擔
    0.55
    ﮅ
    0.55
    禦
    0.52
    璫
    0.46
    ר
    0.46
    繋
    0.45
     來
    0.45
    先進
    0.44
    遅
    0.44
     celor
    0.44
    Activations Density 0.001%

    No Known Activations