© 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. 77384
    Prev
    Next
    INDEX
    Explanations

    private label, conference

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

    instructions and explanations

    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
     长
    0.47
    镀
    0.46
    长时间
    0.44
     tương
    0.43
    习
    0.41
    稀
    0.41
     বিখ্যাত
    0.41
    长
    0.41
    ︰
    0.40
     Icon
    0.40
    POSITIVE LOGITS
    <unused2156>
    0.44
    Brexit
    0.44
     entscheid
    0.44
    ហ៊ុន
    0.43
     permitirá
    0.43
     negotiations
    0.41
     proposals
    0.41
    pern
    0.41
    ในการ
    0.41
     فوری
    0.41
    Activations Density 0.001%

    No Known Activations