© 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. 73223
    Prev
    Next
    INDEX
    Explanations

    detail / details

    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
    ↵↵
    -3.17
     ก็
    -2.58
    "
    -2.34
    戕
    -2.31
     dimly
    -2.23
     startling
    -2.19
     dilapidated
    -2.19
    )));
    -2.19
     представители
    -2.09
     wonderfully
    -2.08
    POSITIVE LOGITS
    With
    2.42
    谞
    2.38
     untuk
    2.38
    菔
    2.33
    ates
    2.30
    を受ける
    2.27
    ではでは
    2.27
    our
    2.23
     für
    2.22
    觧
    2.22
    Activations Density 0.020%

    No Known Activations