© 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. 22-GEMMASCOPE-RES-131K
    7. 64972
    Prev
    Next
    INDEX
    Explanations

    code snippets related to objects

    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_22/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
     astounding
    -1.23
    囘
    -1.23
     puramente
    -1.23
    していない
    -1.20
     amazing
    -1.20
     ་
    -1.19
     insane
    -1.18
     konkret
    -1.17
    ってない
    -1.16
    ⁛
    -1.16
    POSITIVE LOGITS
    ↵
    2.08
     by
    1.45
    ↵↵
    1.27
    埗
    1.22
     jPanel
    1.19
    ）
    1.13
    หวัด
    1.11
     ActionListener
    1.11
     using
    1.09
     rağmen
    1.06
    Activations Density 0.083%

    No Known Activations