© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84809
    Prev
    Next
    INDEX
    Explanations

    hierarchy and nesting depth

    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
     he
    -1.66
    ];
    -1.38
     worauf
    -1.28
     and
    -1.27
    erialized
    -1.26
    関する
    -1.24
    恃
    -1.23
    >'+
    -1.20
    >
    -1.20
    ↵↵
    -1.15
    POSITIVE LOGITS
     znaleźć
    1.62
     生産
    1.60
    Zubereitung
    1.54
    Each
    1.52
     uzyskać
    1.51
    Kommentare
    1.50
    Berat
    1.44
     comples
    1.43
    Beschreibung
    1.43
     your
    1.43
    Activations Density 0.032%

    No Known Activations