© 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. 67182
    Prev
    Next
    INDEX
    Explanations

    HTML/code delimiters

    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
     vlastnosti
    -1.45
     позволяет
    -1.43
     klasa
    -1.31
     כבר
    -1.30
     अलावा
    -1.30
     amplia
    -1.28
    sneaker
    -1.27
    bowling
    -1.27
     produkty
    -1.27
    屺
    -1.27
    POSITIVE LOGITS
    3
    1.73
    也沒
    1.66
    at
    1.55
     смысле
    1.51
    ustering
    1.51
    .
    1.51
    ogues
    1.47
    xff
    1.46
    2
    1.46
     nella
    1.43
    Activations Density 0.019%

    No Known Activations