© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47724
    Prev
    Next
    INDEX
    Explanations

    bitwise operators and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }
    -2.56
     dizzy
    -2.44
    荜
    -2.23
    dotte
    -2.17
    ſſen
    -2.16
    sandalia
    -2.13
    ThemeOverlay
    -2.08
    蜴
    -2.00
     expérience
    -1.99
    櫚
    -1.99
    POSITIVE LOGITS
    y
    2.70
    n
    2.56
    銲
    2.53
    НИК
    2.30
    .,
    2.30
     dzięki
    2.27
    $,
    2.23
    st
    2.17
    งิน
    2.08
    閦
    2.08
    Activations Density 0.000%

    No Known Activations