© 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. 20942
    Prev
    Next
    INDEX
    Explanations

    Names or 'express'

    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
     our
    -1.80
     was
    -1.70
     we
    -1.59
     where
    -1.42
     with
    -1.41
    ing
    -1.39
     which
    -1.38
     together
    -1.38
    쩌
    -1.37
     widespread
    -1.33
    POSITIVE LOGITS
    蹿
    1.53
     horloge
    1.50
     ù
    1.49
    vade
    1.49
    ᠁
    1.45
    䛗
    1.45
     masques
    1.44
     dévelo
    1.43
                    
    1.42
     claire
    1.42
    Activations Density 0.005%

    No Known Activations