© 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. 39507
    Prev
    Next
    INDEX
    Explanations

    internal followed by code keywords

    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
    訁
    -2.63
    ৢ
    -2.25
    쫀
    -2.23
     alkoholu
    -2.13
     které
    -2.02
     และ
    -2.02
    휀
    -1.98
    厹
    -1.95
    windowFixed
    -1.94
     kulinar
    -1.91
    POSITIVE LOGITS
    m
    2.31
    what
    2.03
    r
    2.02
    mente
    1.91
     After
    1.77
     During
    1.77
    idad
    1.74
     this
    1.73
    )　
    1.73
    ver
    1.71
    Activations Density 0.000%

    No Known Activations