© 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. 110686
    Prev
    Next
    INDEX
    Explanations

    percentages of similarity and performance

    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
    鈁
    -0.91
    Ꭸ
    -0.89
    mands
    -0.87
    轳
    -0.86
     klick
    -0.86
    Lihat
    -0.85
    ticism
    -0.85
    酹
    -0.84
     absolut
    -0.83
     trám
    -0.82
    POSITIVE LOGITS
     of
    1.95
     chance
    1.09
     accurate
    1.07
     coverage
    1.05
     accuracy
    1.01
     probability
    0.99
     uptime
    0.97
     humidity
    0.94
     effective
    0.89
     success
    0.85
    Activations Density 0.036%

    No Known Activations