© 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. 113335
    Prev
    Next
    INDEX
    Explanations

    state-of-the-art

    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
    <bos>
    -2.39
    </i>
    -2.02
     formando
    -1.91
     ſuch
    -1.91
     helft
    -1.85
     tijden
    -1.83
     sterren
    -1.82
     patrulla
    -1.79
     soorten
    -1.78
     misc
    -1.76
    POSITIVE LOGITS
    j
    2.77
     of
    2.67
    k
    2.50
    v
    2.48
    f
    2.33
    L
    2.16
    ”、“
    2.14
    l
    2.08
    as
    2.03
     exercer
    2.02
    Activations Density 0.023%

    No Known Activations