© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58999
    Prev
    Next
    INDEX
    Explanations

    quoted 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
     that
    -2.39
     any
    -2.05
     a
    -1.84
     something
    -1.66
     genuine
    -1.63
     todella
    -1.61
    ,&
    -1.61
    毎月
    -1.60
     another
    -1.60
     how
    -1.60
    POSITIVE LOGITS
    <bos>
    1.66
     MILES
    1.55
                
    1.54
    ни
    1.53
        
    1.52
      
    1.51
     "
    1.50
    nebago
    1.48
    などの
    1.48
     möglich
    1.48
    Activations Density 0.022%

    No Known Activations