© 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. 42422
    Prev
    Next
    INDEX
    Explanations

    construction COMPANY

    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
    是
    -2.80
    ꜆
    -2.78
    樒
    -2.73
    )
    -2.67
     pelatih
    -2.59
    쐈
    -2.53
    镦
    -2.50
     Konkur
    -2.48
    苳
    -2.47
    ῞
    -2.47
    POSITIVE LOGITS
     is
    3.38
     We
    3.16
    ”;
    3.03
    ↵
    2.91
    ”,
    2.86
    ),
    2.80
    紧接着
    2.78
    ”.
    2.75
    ”?
    2.72
    ”]
    2.64
    Activations Density 0.020%

    No Known Activations