© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16557
    Prev
    Next
    INDEX
    Explanations

    beginnings of sentences

    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
    Negative Logits
    ⓝ
    -1.00
    },[])
    -0.85
     berichtet
    -0.82
     Atmos
    -0.81
    bitch
    -0.80
    ouds
    -0.79
    topic
    -0.79
     mí
    -0.79
     vieler
    -0.79
    tension
    -0.78
    POSITIVE LOGITS
     these
    1.06
     belong
    1.02
     Ainda
    0.98
    がこの
    0.95
    居然
    0.91
     this
    0.91
    こんな
    0.90
    ècle
    0.90
     Aún
    0.86
     בלב
    0.85
    Activations Density 0.040%

    No Known Activations