© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103971
    Prev
    Next
    INDEX
    Explanations

    usually followed by "The"

    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_34/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
     with
    -1.33
     will
    -1.31
     immerhin
    -1.24
     and
    -1.21
     still
    -1.20
     even
    -1.19
     on
    -1.11
     after
    -1.09
     ändå
    -1.09
     then
    -1.09
    POSITIVE LOGITS
    usually
    1.67
     its
    1.63
     обычно
    1.60
    often
    1.51
    typically
    1.49
    Its
    1.48
     usually
    1.45
     unlike
    1.44
     biasanya
    1.41
    бычно
    1.41
    Activations Density 0.206%

    No Known Activations