© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129500
    Prev
    Next
    INDEX
    Explanations

    that followed by a verb or pronoun

    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
      
    -2.06
     i
    -1.72
     "
    -1.71
     It
    -1.55
     (
    -1.49
    <bos>
    -1.49
     and
    -1.48
     anche
    -1.44
     Also
    -1.41
       
    -1.36
    POSITIVE LOGITS
     that
    1.83
    蛱
    1.77
     abiti
    1.66
     piele
    1.66
     castelo
    1.62
     predecess
    1.55
     cioc
    1.52
     vesel
    1.52
     THOUGHTS
    1.48
     limba
    1.48
    Activations Density 0.057%

    No Known Activations