© 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. 21759
    Prev
    Next
    INDEX
    Explanations

    academic degrees and professions

    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
     their
    -1.51
     OGSÅ
    -1.43
     verhind
    -1.41
    ܜ
    -1.35
     sobot
    -1.34
     deň
    -1.34
     yayınları
    -1.34
     wła
    -1.33
    droje
    -1.32
     stycz
    -1.31
    POSITIVE LOGITS
     of
    1.95
     from
    1.54
     well
    1.38
     этого
    1.34
     out
    1.25
     but
    1.16
     ,
    1.15
    #%%
    
    1.15
    ]}>
    1.14
    VIRGO
    1.14
    Activations Density 0.145%

    No Known Activations