© 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. 22-GEMMASCOPE-RES-131K
    7. 129999
    Prev
    Next
    INDEX
    Explanations

    creation and establishment

    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_22/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
     their
    -1.44
     variety
    -1.41
     different
    -1.34
     varied
    -1.33
     assorted
    -1.31
     múltiples
    -1.30
     still
    -1.25
     distintas
    -1.20
     l
    -1.17
     diferite
    -1.17
    POSITIVE LOGITS
     for
    1.85
     to
    1.74
     ıs
    1.30
     linge
    1.28
     specifik
    1.23
    phòng
    1.22
     producent
    1.21
     philosophie
    1.20
     rése
    1.20
     in
    1.20
    Activations Density 0.092%

    No Known Activations