© 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. 14639
    Prev
    Next
    INDEX
    Explanations

    foundation stage reports

    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
    
    -1.52
     fiscale
    -1.47
     anunció
    -1.45
     jät
    -1.43
     enthou
    -1.40
     vitale
    -1.38
     menggel
    -1.36
     tesettür
    -1.36
     安装
    -1.35
    鬈
    -1.35
    POSITIVE LOGITS
     when
    1.32
     भी
    1.30
    ;#
    1.29
     on
    1.25
     in
    1.23
     get
    1.21
     or
    1.20
    These
    1.20
     even
    1.20
     it
    1.20
    Activations Density 0.051%

    No Known Activations