© 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. 10-GEMMASCOPE-RES-131K
    4. 104454
    Prev
    Next
    INDEX
    Explanations

    all plus descriptive verbs

    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
     of
    -3.16
     it
    -2.08
    ….
    -2.02
     is
    -1.80
     but
    -1.77
     These
    -1.72
     if
    -1.71
    ;
    -1.68
    US
    -1.67
    These
    -1.66
    POSITIVE LOGITS
    estructura
    1.79
    
    1.77
     zegt
    1.66
     vertelt
    1.63
    capulco
    1.61
    揹
    1.60
     DIFFERENCE
    1.59
    輅
    1.58
     dacht
    1.57
     krijg
    1.56
    Activations Density 0.020%

    No Known Activations