© 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. 40100
    Prev
    Next
    INDEX
    Explanations

    admitting wrong

    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
    剮
    -2.36
     jika
    -1.91
     если
    -1.71
    
    -1.67
     jeśli
    -1.66
    ఙ
    -1.62
     nếu
    -1.59
    hmä
    -1.56
    文化的
    -1.53
    典型的
    -1.53
    POSITIVE LOGITS
     there
    1.91
     about
    1.90
     Eröffnung
    1.55
     they
    1.55
     Mehrheit
    1.52
     ataupun
    1.47
    but
    1.45
     Ankunft
    1.42
     siguran
    1.38
     sämtliche
    1.36
    Activations Density 0.013%

    No Known Activations