© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47427
    Prev
    Next
    INDEX
    Explanations

    transforming, striking

    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
     one
    -0.83
     Schaden
    -0.82
     cze
    -0.80
     Побе
    -0.78
    izam
    -0.78
     most
    -0.78
     Vö
    -0.76
     rima
    -0.76
    dampak
    -0.76
     Савезне
    -0.75
    POSITIVE LOGITS
     могут
    0.92
     取り付け
    0.87
     _.
    0.85
    ②
    0.84
     هنوز
    0.82
     frische
    0.82
    もっと
    0.80
    ïdes
    0.79
     kürzlich
    0.79
     sichere
    0.79
    Activations Density 0.007%

    No Known Activations