© 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. 16690
    Prev
    Next
    INDEX
    Explanations

    position and direction

    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
     içinde
    -0.99
    RGBA
    -0.96
    HV
    -0.90
     Hobbes
    -0.90
     edição
    -0.90
     wiecz
    -0.88
    ,'
    -0.88
    RF
    -0.87
     africaine
    -0.86
     Boeing
    -0.85
    POSITIVE LOGITS
     laiss
    0.93
     Anges
    0.89
     disant
    0.88
     männ
    0.87
     useParams
    0.87
     garant
    0.86
    attended
    0.85
     chaine
    0.84
     takich
    0.84
     läm
    0.84
    Activations Density 0.007%

    No Known Activations