© 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. 130884
    Prev
    Next
    INDEX
    Explanations

    what people do

    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
     and
    -1.98
     וכן
    -1.53
     or
    -1.40
    PENDAHULUAN
    -1.39
    badan
    -1.38
     oraz
    -1.33
     bekämp
    -1.33
    絝
    -1.32
     kämp
    -1.31
    odine
    -1.30
    POSITIVE LOGITS
     have
    2.39
     will
    1.82
    が
    1.79
     know
    1.77
    '
    1.59
     would
    1.59
     experience
    1.55
     think
    1.51
     still
    1.48
     use
    1.45
    Activations Density 0.025%

    No Known Activations