© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104828
    Prev
    Next
    INDEX
    Explanations

    us for

    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
     vixion
    -1.82
     stiker
    -1.76
     $_=
    -1.71
    𐐀
    -1.68
     daewoo
    -1.68
     nuov
    -1.67
     galeri
    -1.66
     estadounid
    -1.63
    Ꮴ
    -1.60
     milano
    -1.59
    POSITIVE LOGITS
     at
    2.16
     in
    1.76
     Only
    1.63
     as
    1.58
     Not
    1.57
     primera
    1.57
     nicht
    1.52
     Now
    1.50
     In
    1.48
     ''
    1.44
    Activations Density 0.016%

    No Known Activations