© 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. 22-GEMMASCOPE-RES-131K
    7. 98212
    Prev
    Next
    INDEX
    Explanations

    technologies and techniques

    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
     because
    -1.65
     or
    -1.59
     for
    -1.44
     their
    -1.36
     when
    -1.33
    誦
    -1.31
     autobús
    -1.31
     eight
    -1.30
     each
    -1.28
     all
    -1.22
    POSITIVE LOGITS
     to
    1.92
     silva
    1.16
     美術
    1.14
     rivi
    1.09
     feront
    1.06
     vider
    1.06
     juventus
    1.04
     pixar
    1.03
    formerly
    1.02
     persil
    1.02
    Activations Density 0.089%

    No Known Activations