© 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. 44015
    Prev
    Next
    INDEX
    Explanations

    platform features and services

    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
    Sudah
    -1.35
     élégante
    -1.32
     fiscale
    -1.27
    return
    -1.24
     pâtes
    -1.21
    ņu
    -1.19
    HasBeenSet
    -1.19
    Ольга
    -1.18
     alkoholu
    -1.16
     enthou
    -1.16
    POSITIVE LOGITS
     "
    1.34
     or
    1.30
    <
    1.20
    、
    1.18
     then
    1.15
     they
    1.15
     from
    1.13
     now
    1.13
      
    1.13
     sogen
    1.13
    Activations Density 0.123%

    No Known Activations