© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73578
    Prev
    Next
    INDEX
    Explanations

    forms of to be + adjective

    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
    尤其是
    -0.95
    primaryStage
    -0.93
     особенно
    -0.93
    loggen
    -0.91
    zustand
    -0.91
    getBounding
    -0.90
    ('-'
    -0.90
    sekten
    -0.90
     "/",
    -0.89
    styp
    -0.89
    POSITIVE LOGITS
     into
    1.27
     also
    1.17
     not
    1.09
     now
    1.03
     in
    1.00
     always
    0.90
     still
    0.90
     oblivion
    0.89
     yet
    0.86
     used
    0.85
    Activations Density 0.012%

    No Known Activations