© 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. 204717
    Prev
    Next
    INDEX
    Explanations

    Supreme Court

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

    foreign languages and related concepts

    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
     insurg
    0.52
     に
    0.48
    (
    0.47
     SIP
    0.45
     anarchist
    0.45
    {
    0.44
     BFF
    0.44
    ‎
    0.44
    (?:
    0.43
    (−
    0.42
    POSITIVE LOGITS
    érons
    0.52
    тами
    0.51
    দেখ
    0.51
    льников
    0.51
    aten
    0.50
    탓
    0.50
    त्तीस
    0.48
    entingan
    0.48
     видеть
    0.47
    че
    0.46
    Activations Density 0.000%

    No Known Activations