© 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. 34-GEMMASCOPE-RES-131K
    7. 106495
    Prev
    Next
    INDEX
    Explanations

    "We" 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_34/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
     skolan
    -1.05
    لينا
    -1.02
     mehrerer
    -1.02
    tså
    -1.00
     bija
    -0.99
     itself
    -0.97
     angepasst
    -0.92
    Cuándo
    -0.92
    非常好
    -0.91
     polisi
    -0.89
    POSITIVE LOGITS
     believe
    1.69
     know
    1.57
     hope
    1.55
     at
    1.47
     also
    1.34
     invite
    1.34
     love
    1.27
     understand
    1.27
     want
    1.26
     belief
    1.20
    Activations Density 0.083%

    No Known Activations