© 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. 245449
    Prev
    Next
    INDEX
    Explanations

    correspondence as, few superb, bunk room, unity agreement

    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
    트를
    0.49
    ادم
    0.48
     배
    0.48
    inya
    0.47
    었다
    0.46
    ibraries
    0.45
    비를
    0.45
    uppe
    0.45
    бити
    0.44
     엄청
    0.44
    POSITIVE LOGITS
    ೋಜನ
    0.45
     primordial
    0.44
     considérer
    0.44
     trifle
    0.43
     forgo
    0.43
    鈍
    0.43
     speedometer
    0.43
     which
    0.42
     hlavní
    0.42
    which
    0.42
    Activations Density 0.000%

    No Known Activations