© 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. 102127
    Prev
    Next
    INDEX
    Explanations

    curtain

    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
     \_
    -3.16
    谘
    -2.61
    there
    -2.56
    óricos
    -2.52
    텃
    -2.50
    ндарт
    -2.48
     باسلام
    -2.47
    謦
    -2.44
     —
    -2.36
     Verantwort
    -2.22
    POSITIVE LOGITS
    '
    2.70
      
    2.52
    摭
    2.50
    锕
    2.47
    ⑊
    2.42
    );
    2.39
    )--
    2.39
     dando
    2.34
    ).
    2.33
     totalmente
    2.31
    Activations Density 0.004%

    No Known Activations