© 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. 135831
    Prev
    Next
    INDEX
    Explanations

    products, developments, statement, weekend

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

    witty names, company, spatula

    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
    的变化
    0.47
     უკ
    0.44
     धारण
    0.44
     develops
    0.43
     ἀ
    0.43
    的
    0.43
     நம்
    0.42
    Alexander
    0.42
    의
    0.42
    Ă
    0.41
    POSITIVE LOGITS
     West
    0.46
     empresarios
    0.46
    oters
    0.46
     सितारों
    0.46
     वेस्ट
    0.46
     landing
    0.45
     दुरु
    0.45
    s
    0.45
     इंतजाम
    0.44
    age
    0.44
    Activations Density 0.000%

    No Known Activations