© 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. 112494
    Prev
    Next
    INDEX
    Explanations

    Calendar, mechanical, mountain, scheduler

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

    code examples and technical descriptions

    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
    ᓄ
    0.56
    ୯
    0.54
    𝖺
    0.53
     zie
    0.49
     पैसों
    0.49
    ំ
    0.49
    اً
    0.47
     घंटों
    0.47
    ﯽ
    0.47
    ᆷ
    0.46
    POSITIVE LOGITS
     מק
    0.44
     shoulder
    0.43
     Mountain
    0.43
     洋
    0.43
     mechanical
    0.42
     недостаточно
    0.42
     canyon
    0.42
    scheduler
    0.41
     mecánica
    0.41
     প্রশস্ত
    0.40
    Activations Density 0.001%

    No Known Activations