© 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. 43943
    Prev
    Next
    INDEX
    Explanations

    email recipients

    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
    鹛
    -2.09
    '
    -2.09
    汌
    -2.00
     занимает
    -1.99
     and
    -1.92
     позволит
    -1.91
    O
    -1.89
     pertenec
    -1.88
    柃
    -1.88
     соответствует
    -1.83
    POSITIVE LOGITS
     –
    2.41
    剮
    2.28
     —
    2.20
    卨
    2.19
    ется
    2.09
    Đăng
    2.06
     häufigsten
    2.00
    整个
    1.99
    团队
    1.98
    вгений
    1.98
    Activations Density 0.012%

    No Known Activations