© 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. 22-GEMMASCOPE-RES-131K
    7. 72249
    Prev
    Next
    INDEX
    Explanations

    section introductions citations

    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
     pittores
    -1.30
     suppos
    -1.27
     BEAUT
    -1.24
     integrante
    -1.24
     bedien
    -1.23
    Carreira
    -1.22
     endeavouring
    -1.22
    😕
    -1.20
     pemberian
    -1.18
     acqua
    -1.17
    POSITIVE LOGITS
     ongoing
    1.55
     even
    1.52
     other
    1.45
     verdaderas
    1.39
     not
    1.39
     first
    1.36
     varandra
    1.34
     more
    1.34
     T
    1.29
     others
    1.29
    Activations Density 0.004%

    No Known Activations