© 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. 22-GEMMASCOPE-RES-131K
    7. 98335
    Prev
    Next
    INDEX
    Explanations

    from './' or '../'

    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_22/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
     "
    -1.51
     l
    -1.45
    up
    -1.33
    r
    -1.33
    ed
    -1.32
    ?"
    -1.31
     only
    -1.30
     find
    -1.27
     $
    -1.26
     if
    -1.25
    POSITIVE LOGITS
     插图
    1.52
    ֯
    1.48
    蘧
    1.44
     penutup
    1.41
     عراق
    1.39
    Enfant
    1.37
    ſi
    1.36
    
    1.35
     amorti
    1.35
    Asie
    1.34
    Activations Density 0.009%

    No Known Activations