© 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. 68412
    Prev
    Next
    INDEX
    Explanations

    introduction to work and research

    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
     toalla
    -1.38
     its
    -1.19
     membag
    -1.13
    pantalon
    -1.08
     piratas
    -1.04
     another
    -1.02
     Bildschirm
    -1.01
    opie
    -1.01
    uglify
    -1.00
    Ecotoxicity
    -1.00
    POSITIVE LOGITS
     this
    1.07
    所以在
    1.00
     utafiti
    0.98
    9
    0.97
     hierv
    0.96
    úmer
    0.96
     haup
    0.93
    tisme
    0.91
     we
    0.91
    cuits
    0.91
    Activations Density 0.020%

    No Known Activations