© 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. 112690
    Prev
    Next
    INDEX
    Explanations

    caught up in

    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
     säker
    -1.52
    :'
    -1.47
    :""
    -1.45
    覿
    -1.43
     или
    -1.43
     после
    -1.42
    ""
    -1.42
     '>
    -1.41
     teratur
    -1.41
    ---------
    -1.37
    POSITIVE LOGITS
     notables
    1.69
     everything
    1.54
     the
    1.49
    iniest
    1.42
    גים
    1.42
     includes
    1.38
    をご覧ください
    1.38
     Reduces
    1.37
    的一切
    1.33
    Karakteristik
    1.31
    Activations Density 0.052%

    No Known Activations