© 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. 129039
    Prev
    Next
    INDEX
    Explanations

    divide, transfer, pour ingredients

    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
     sapatos
    -1.55
     óculos
    -1.55
     this
    -1.48
     différents
    -1.48
     that
    -1.45
     väga
    -1.45
     rất
    -1.42
     berço
    -1.42
    も行
    -1.41
     dokonce
    -1.39
    POSITIVE LOGITS
     from
    1.88
     by
    1.83
     at
    1.78
     first
    1.65
     began
    1.63
     out
    1.62
     eight
    1.47
     still
    1.45
     sobą
    1.45
     red
    1.38
    Activations Density 0.029%

    No Known Activations