© 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. 25941
    Prev
    Next
    INDEX
    Explanations

    bipolar disorder or OD matrix

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

    profile, doing, seen, you, weekend, levels

    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
    s
    0.62
    m
    0.51
    К
    0.51
    e
    0.46
    eurs
    0.46
    arya
    0.46
    nn
    0.46
     fortunes
    0.45
     labores
    0.45
    Бу
    0.45
    POSITIVE LOGITS
     খ
    0.49
     ගැන
    0.48
     সমাপ্ত
    0.46
     tk
    0.46
     সংগ্রহ
    0.46
     সমস্যা
    0.45
     čtyř
    0.44
     问题
    0.44
     Sebuah
    0.43
     BGPS
    0.43
    Activations Density 0.000%

    No Known Activations