© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84317
    Prev
    Next
    INDEX
    Explanations

    ever followed by verbs or adverbs

    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
    ’
    -2.20
     behandel
    -1.78
    ↵↵↵
    -1.75
     Erfüllung
    -1.74
     vijf
    -1.70
    こだ
    -1.69
    discussed
    -1.66
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.63
     utilisés
    -1.61
    Í
    -1.61
    POSITIVE LOGITS
    。”
    1.98
    ꠥ
    1.84
    silien
    1.84
    数十
    1.82
    )$,
    1.80
     humaine
    1.74
     of
    1.71
    AddHtmlAttribute
    1.70
    All
    1.69
     supremely
    1.69
    Activations Density 0.003%

    No Known Activations