© 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. 8920
    Prev
    Next
    INDEX
    Explanations

    efficient word followed by description

    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
     exceptionally
    -3.34
     amazingly
    -3.23
     quintessential
    -3.20
     delightfully
    -3.09
     unbelievably
    -3.09
     soooo
    -3.03
     decidedly
    -3.02
    actéristi
    -3.00
     superb
    -2.91
     ridiculously
    -2.88
    POSITIVE LOGITS
    '
    3.83
     While
    3.55
     seems
    3.45
     provides
    3.31
    Without
    3.23
     wants
    3.20
    Even
    3.20
     Although
    3.19
     makes
    3.17
    There
    3.13
    Activations Density 0.009%

    No Known Activations