© 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. 28992
    Prev
    Next
    INDEX
    Explanations

    my husband

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

    ip, back, studies

    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
     సహాయ
    0.48
     Infrastructure
    0.46
     მი
    0.45
     Biblia
    0.43
    牘
    0.43
     তারা
    0.41
    员
    0.41
     लिखा
    0.41
    辅
    0.41
    覆盖
    0.40
    POSITIVE LOGITS
    ंजक
    0.47
     ژوند
    0.46
    ceptible
    0.44
     droplets
    0.43
    drink
    0.42
    nice
    0.41
    phases
    0.40
    ها
    0.39
    choices
    0.39
    flowing
    0.39
    Activations Density 0.000%

    No Known Activations