© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129703
    Prev
    Next
    INDEX
    Explanations

    innovation and research

    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
     großes
    -1.70
     razie
    -1.51
     starken
    -1.51
     ganzes
    -1.49
     erfolgre
    -1.49
     químico
    -1.48
     äußerst
    -1.48
     that
    -1.46
    Från
    -1.45
     riserv
    -1.44
    POSITIVE LOGITS
     my
    1.52
     me
    1.48
     in
    1.48
     Player
    1.31
     Clou
    1.24
     Child
    1.20
    },
    1.20
    ),
    1.19
     Fab
    1.16
     fass
    1.16
    Activations Density 0.141%

    No Known Activations