© 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. 73650
    Prev
    Next
    INDEX
    Explanations

    CSS body declarations

    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
     então
    -1.49
    rdoba
    -1.47
    氿
    -1.44
     eivät
    -1.39
    ppchen
    -1.38
     entonces
    -1.38
    tabile
    -1.36
    oges
    -1.34
     Then
    -1.32
     MÁS
    -1.32
    POSITIVE LOGITS
    /
    1.69
    },
    1.49
    .
    1.40
    '
    1.35
    (
    1.34
    {
    1.34
    ,
    1.30
    \
    1.28
    mathrm
    1.27
    ↵↵
    1.27
    Activations Density 0.018%

    No Known Activations