© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14805
    Prev
    Next
    INDEX
    Explanations

    New York Times, Civil rights icon, University of

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

    topics followed by actions or roles

    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_16k_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
     abelian
    0.33
     گیا
    0.30
     landscaped
    0.30
     campus
    0.29
    누
    0.29
    GBuf
    0.29
     Graf
    0.29
    Pul
    0.29
     ну
    0.28
     sous
    0.28
    POSITIVE LOGITS
     مقابلہ
    0.35
    をはじめ
    0.31
     Brandt
    0.30
    。『
    0.29
     averse
    0.28
    🙅
    0.28
    :///
    0.27
    ❌
    0.27
    माने
    0.27
     একদিকে
    0.27
    Activations Density 0.064%

    No Known Activations