© 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. 102657
    Prev
    Next
    INDEX
    Explanations

    please use our

    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
     should
    -1.87
     comunit
    -1.55
     boste
    -1.47
     miniatura
    -1.45
     bolsa
    -1.41
    のほうが
    -1.40
    zole
    -1.39
    ཋ
    -1.38
    خاب
    -1.37
     suicidio
    -1.37
    POSITIVE LOGITS
    3
    1.88
    4
    1.76
    8
    1.69
    ,
    1.69
    2
    1.60
    7
    1.55
     our
    1.52
    5
    1.50
     innym
    1.49
     in
    1.48
    Activations Density 0.136%

    No Known Activations