© 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. 156316
    Prev
    Next
    INDEX
    Explanations

    expectation that

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

    distinguish between

    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
    ﺩ
    0.48
    яс
    0.42
    intu
    0.41
    Vecchio
    0.39
     лишь
    0.38
    visible
    0.38
    יו
    0.37
    ຈ
    0.37
    вере
    0.37
    види
    0.37
    POSITIVE LOGITS
     अनेक
    0.54
     ऑर्गे
    0.53
     ကု
    0.51
     reactors
    0.50
     giết
    0.47
     নানা
    0.47
     अराउंड
    0.47
     इंटेल
    0.47
     médec
    0.46
     szervez
    0.46
    Activations Density 0.000%

    No Known Activations