© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 197990
    Prev
    Next
    INDEX
    Explanations

    script style markdown breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lle
    0.39
     категории
    0.39
    Ʌ
    0.38
    helle
    0.38
    ome
    0.37
    腊
    0.37
    /><
    0.37
    ́ng
    0.37
    rakash
    0.37
    inken
    0.36
    POSITIVE LOGITS
    Iris
    1.13
     iris
    1.12
     Iris
    1.10
    iris
    0.98
    IRIS
    0.92
    鸢
    0.78
     mt
    0.68
    铱
    0.59
     Cars
    0.57
    Cars
    0.55
    Activations Density 0.000%

    No Known Activations