© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90312
    Prev
    Next
    INDEX
    Explanations

    history and existence

    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
     aktive
    -1.35
     fabrik
    -1.34
     melk
    -1.33
     כבר
    -1.31
     minimale
    -1.30
     velg
    -1.30
     universelle
    -1.27
     olie
    -1.25
     ferien
    -1.24
    kennen
    -1.23
    POSITIVE LOGITS
    It
    1.59
    The
    1.33
    });
    1.30
    </h5>
    1.23
    ナソニック
    1.20
    There
    1.19
    You
    1.15
     zarówno
    1.14
    ....
    1.13
    People
    1.13
    Activations Density 0.088%

    No Known Activations