© 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. 80895
    Prev
    Next
    INDEX
    Explanations

    Crock Pot

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

    four different images, opera, different subsets, SIE file

    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
    бут
    0.46
     zählt
    0.45
    ണ്‍
    0.44
     tz
    0.43
    َم
    0.43
    న్‌
    0.43
    ্ত্র
    0.43
    льный
    0.41
    pg
    0.40
    ড়া
    0.40
    POSITIVE LOGITS
     rinsing
    0.55
     със
    0.54
    ት
    0.54
     עם
    0.52
    umy
    0.51
     ऑलरेडी
    0.50
     имају
    0.49
     умови
    0.49
    workouts
    0.49
     प्राय
    0.49
    Activations Density 0.000%

    No Known Activations