© 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. 80766
    Prev
    Next
    INDEX
    Explanations

    documentation comments

    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
     on
    -2.08
     its
    -2.03
     to
    -1.99
     it
    -1.95
     by
    -1.94
     or
    -1.88
     at
    -1.86
     with
    -1.73
     the
    -1.58
     helps
    -1.55
    POSITIVE LOGITS
     mauva
    1.91
    屨
    1.88
    衚
    1.86
     Seigneur
    1.76
    presumably
    1.73
    THEN
    1.71
     türkiye
    1.70
     plancha
    1.70
    ahh
    1.67
     lapin
    1.66
    Activations Density 0.009%

    No Known Activations