© 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. 110811
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
     घटना
    -0.73
     Dessa
    -0.72
    olella
    -0.69
    noy
    -0.69
    utando
    -0.68
     getObject
    -0.68
     iLocal
    -0.67
     SAME
    -0.67
     методи
    -0.66
     tokio
    -0.66
    POSITIVE LOGITS
    Arr
    1.10
     bArr
    1.00
     str
    0.98
     variance
    0.86
     Arr
    0.85
     cls
    0.83
    str
    0.83
     stratum
    0.78
     prec
    0.75
    GroupBy
    0.73
    Activations Density 0.009%

    No Known Activations