© 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. 85774
    Prev
    Next
    INDEX
    Explanations

    how something is done

    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
        
    -1.71
    část
    -1.67
     Verlauf
    -1.55
      
    -1.54
     recent
    -1.50
       
    -1.49
    凝土
    -1.49
    猁
    -1.48
    grä
    -1.48
     beträ
    -1.48
    POSITIVE LOGITS
     of
    2.44
     we
    2.09
    >
    1.80
     которые
    1.72
     he
    1.65
     they
    1.63
     uwe
    1.61
    )
    1.60
    ()
    1.60
    //{
    1.54
    Activations Density 0.015%

    No Known Activations