© 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. 14298
    Prev
    Next
    INDEX
    Explanations

    ANN model or techniques

    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
    0
    -3.78
    Of
    -3.63
    4
    -3.38
    5
    -3.31
    -
    -3.31
    6
    -3.22
    It
    -3.11
    8
    -3.11
    Instead
    -3.08
    2
    -3.05
    POSITIVE LOGITS
    
    2.70
    𝗠
    2.66
    饧
    2.55
    餿
    2.50
    зации
    2.39
    家主
    2.38
    鋌
    2.34
    стандарт
    2.31
    菘
    2.27
    窳
    2.23
    Activations Density 0.001%

    No Known Activations