© 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. 113399
    Prev
    Next
    INDEX
    Explanations

    citations and metadata

    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
     of
    -1.75
     ',',
    -1.36
    תיים
    -1.36
     klarer
    -1.34
     경우
    -1.32
     hvis
    -1.31
     funda
    -1.30
    Zs
    -1.29
     menim
    -1.25
     Negra
    -1.25
    POSITIVE LOGITS
     from
    1.48
     date
    1.38
     Процитовано
    1.34
    蛱
    1.34
     Anhänger
    1.34
    řízení
    1.24
     brinquedo
    1.24
    dzić
    1.24
     stratégique
    1.21
     digne
    1.20
    Activations Density 0.004%

    No Known Activations