© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43162
    Prev
    Next
    INDEX
    Explanations

    support team or issue

    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
     other
    -1.68
     longtime
    -1.58
     („
    -1.51
     use
    -1.43
    另一
    -1.39
     $
    -1.38
     beschäf
    -1.37
     Unglück
    -1.37
     his
    -1.34
     Töchter
    -1.34
    POSITIVE LOGITS
    他們
    1.57
    🤎
    1.53
     they
    1.45
     tige
    1.39
     boda
    1.39
     paham
    1.36
    得不
    1.33
    涐
    1.31
    aterally
    1.31
    狀況
    1.30
    Activations Density 0.026%

    No Known Activations