© 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. 51963
    Prev
    Next
    INDEX
    Explanations

    such as

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

    multilingual identifiers and currencies

    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
    бавля
    0.55
    オ
    0.52
    プ
    0.52
    ANIA
    0.49
    чь
    0.47
    我們的
    0.47
    SECTION
    0.46
    沒
    0.46
    ゲット
    0.46
    VER
    0.45
    POSITIVE LOGITS
     thought
    0.46
     နှင့်
    0.41
     Bedürfnisse
    0.40
     কার্যক্রম
    0.39
     wanting
    0.39
     Architectural
    0.39
     为
    0.39
     گفته
    0.39
     prepared
    0.38
     garments
    0.38
    Activations Density 0.000%

    No Known Activations