© 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. 57954
    Prev
    Next
    INDEX
    Explanations

    ratings and scores

    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
     rashes
    -0.88
    oczes
    -0.79
    
    -0.78
    יך
    -0.77
    😮
    -0.72
     ಪ್ರ
    -0.72
     аз
    -0.72
    쌤
    -0.72
    SKE
    -0.71
    шими
    -0.71
    POSITIVE LOGITS
     rewatch
    1.09
     watched
    0.98
     coisas
    0.90
    rated
    0.87
     Mungkin
    0.86
     leps
    0.84
     lixo
    0.83
     Bemerkungen
    0.83
     palha
    0.82
     Moderna
    0.81
    Activations Density 0.007%

    No Known Activations