© 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. 112484
    Prev
    Next
    INDEX
    Explanations

    in a location

    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
    .
    -3.00
    The
    -2.69
    4
    -2.61
     Another
    -2.47
    3
    -2.38
    6
    -2.31
    According
    -2.22
    8
    -2.14
    2
    -2.14
    9
    -2.08
    POSITIVE LOGITS
     a
    1.89
     geweest
    1.82
     an
    1.78
    )...
    1.77
     such
    1.77
     \&
    1.72
     by
    1.71
     it
    1.68
     also
    1.66
    瓛
    1.65
    Activations Density 0.008%

    No Known Activations