© 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. 10-GEMMASCOPE-RES-131K
    7. 68800
    Prev
    Next
    INDEX
    Explanations

    specific needs of

    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_10/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
     elaborado
    -1.91
    '
    -1.60
     inspirado
    -1.54
     decorado
    -1.53
     versátil
    -1.52
    attempts
    -1.50
     folos
    -1.50
    antaranya
    -1.49
     adaptado
    -1.48
     destacado
    -1.46
    POSITIVE LOGITS
     you
    1.80
    IENTS
    1.76
     Firstly
    1.63
     kedua
    1.63
    蛧
    1.61
     Furthermore
    1.59
    erobic
    1.57
    麈
    1.56
     radeon
    1.55
    踯
    1.55
    Activations Density 0.013%

    No Known Activations