© 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. 60281
    Prev
    Next
    INDEX
    Explanations

    adjectives describing characteristics

    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
     the
    -2.53
     or
    -2.27
     some
    -1.83
     if
    -1.82
     an
    -1.81
     one
    -1.76
     perhaps
    -1.74
     in
    -1.73
     from
    -1.72
     another
    -1.67
    POSITIVE LOGITS
     mêmes
    1.77
     bascul
    1.61
     素描
    1.55
    zember
    1.53
    Its
    1.50
     véhic
    1.48
     fonctionner
    1.47
    很喜欢
    1.46
     énorm
    1.46
    gives
    1.46
    Activations Density 0.159%

    No Known Activations