© 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. 71819
    Prev
    Next
    INDEX
    Explanations

    straight games

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

    findings, review, availability, dashboard

    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
     نعمت
    0.42
    ug
    0.41
    ভাবে
    0.40
    ш
    0.39
    awai
    0.39
    もら
    0.38
    peek
    0.37
    Vectors
    0.37
    があって
    0.37
     invers
    0.37
    POSITIVE LOGITS
    🆁
    0.55
    뤽
    0.55
     polu
    0.54
    𝙏
    0.54
     नहीं
    0.54
     राधे
    0.53
    욤
    0.53
     sním
    0.52
     항공
    0.51
     ಅಧಿಕಾರಿ
    0.50
    Activations Density 0.001%

    No Known Activations