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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83151
    Prev
    Next
    INDEX
    Explanations

    directory paths and names

    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
     or
    -1.01
     uniquely
    -0.89
     both
    -0.89
     seemed
    -0.88
     १
    -0.86
    LOS
    -0.86
     what
    -0.85
     causing
    -0.84
     stating
    -0.83
     ♥
    -0.83
    POSITIVE LOGITS
    (>
    0.83
     surpren
    0.82
    Crus
    0.82
     miércoles
    0.81
    работа
    0.80
     savent
    0.79
     humanidad
    0.78
    龠
    0.78
     natürlich
    0.78
     opak
    0.78
    Activations Density 0.017%

    No Known Activations