© 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. 158760
    Prev
    Next
    INDEX
    Explanations

    methods and historical examples

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

    specific word followed by context

    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
     类型
    0.52
     ዓይ
    0.49
    蕊
    0.47
     âg
    0.47
     ملین
    0.46
     nay
    0.46
     Нача
    0.45
     层
    0.45
     مِنْ
    0.45
     فِي
    0.44
    POSITIVE LOGITS
     hospitable
    0.48
    ttps
    0.47
    లూ
    0.47
    sprogram
    0.47
    กระ
    0.46
    oste
    0.46
     elegan
    0.45
     populist
    0.45
    ador
    0.45
    سلام
    0.45
    Activations Density 0.001%

    No Known Activations