© 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. 10-GEMMASCOPE-RES-131K
    7. 100975
    Prev
    Next
    INDEX
    Explanations

    starts sentences with "And"

    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_10/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
    There
    -2.23
    Perhaps
    -2.20
    If
    -2.13
    While
    -2.03
    What
    -2.00
    Those
    -2.00
    Surprisingly
    -2.00
    Though
    -1.84
    Although
    -1.82
    Whenever
    -1.80
    POSITIVE LOGITS
     then
    2.42
     they
    2.27
    h
    2.00
     how
    1.97
    begin
    1.94
     actually
    1.93
    re
    1.92
     again
    1.86
     supposed
    1.79
     later
    1.75
    Activations Density 0.008%

    No Known Activations