© 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. 39996
    Prev
    Next
    INDEX
    Explanations

    let's followed by a verb

    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
     that
    -2.06
    
    -2.03
     this
    -2.03
    PENDAHULUAN
    -1.99
     dimas
    -1.97
     mengganggu
    -1.95
     نکنید
    -1.95
     any
    -1.91
     meningkat
    -1.90
     one
    -1.87
    POSITIVE LOGITS
    "
    2.47
    an
    2.42
    '
    2.39
    as
    2.03
    al
    1.98
    ar
    1.92
    \
    1.87
    ’
    1.86
      
    1.86
    ‐
    1.84
    Activations Density 0.009%

    No Known Activations