© 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. 62626
    Prev
    Next
    INDEX
    Explanations

    Kota Tinggi Museum

    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
    Negative Logits
    が届
    -0.96
     terraza
    -0.91
    чё
    -0.90
     nunc
    -0.88
     yarış
    -0.83
    because
    -0.83
     gehouden
    -0.82
     krep
    -0.81
    鵑
    -0.79
     mutfak
    -0.78
    POSITIVE LOGITS
    wd
    0.81
    glement
    0.81
    кота
    0.78
    w
    0.78
     ikiwa
    0.76
    ']
    0.75
    ;;;;
    0.75
    '),
    0.74
    conf
    0.74
    hmac
    0.73
    Activations Density 0.008%

    No Known Activations