© 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. 67414
    Prev
    Next
    INDEX
    Explanations

    crater and meteorite

    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
     メニュー
    -3.16
    獃
    -2.81
    Ꭳ
    -2.64
    棪
    -2.64
    ઁ
    -2.59
    Ꮷ
    -2.52
    瀦
    -2.48
     medes
    -2.45
    慤
    -2.42
    ൎ
    -2.39
    POSITIVE LOGITS
     --
    2.66
    i
    2.58
     '
    2.58
     ​
    2.52
    -
    2.48
    </strong>
    2.45
    <em>
    2.44
     â
    2.39
    </h4>
    2.31
    у
    2.23
    Activations Density 0.001%

    No Known Activations