© 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. 39918
    Prev
    Next
    INDEX
    Explanations

    HTML structure classes

    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
     zimowe
    -1.41
     inicialmente
    -1.38
     there
    -1.37
    、“
    -1.37
    “
    -1.28
    かれる
    -1.27
     fossero
    -1.27
    しゃれ
    -1.24
     město
    -1.24
    pieza
    -1.21
    POSITIVE LOGITS
    
    1.74
     único
    1.64
    各样的
    1.52
     of
    1.49
    </h6>
    1.46
     större
    1.41
    はこの
    1.41
    etone
    1.39
     "`
    1.38
    had
    1.38
    Activations Density 0.009%

    No Known Activations