© 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. 47068
    Prev
    Next
    INDEX
    Explanations

    document class declarations

    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
    درسة
    -0.87
     mieli
    -0.83
     hendes
    -0.81
    --*/
    -0.79
     Juin
    -0.77
    punctuation
    -0.77
    (||
    -0.76
     помещений
    -0.76
    waite
    -0.75
    thog
    -0.75
    POSITIVE LOGITS
    acidade
    0.82
     Krise
    0.74
    Lut
    0.72
    它們
    0.71
    akos
    0.71
     sermon
    0.71
    }/*
    0.69
    וֹ
    0.69
    っています
    0.69
    ühl
    0.68
    Activations Density 0.013%

    No Known Activations