© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65961
    Prev
    Next
    INDEX
    Explanations

    on the one hand

    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
     biografias
    -0.83
     इस
    -0.78
    IndexPath
    -0.78
    PEI
    -0.77
    ého
    -0.75
     Мин
    -0.73
     kän
    -0.71
    addPreferredGap
    -0.70
     HFILL
    -0.69
     Besonder
    -0.68
    POSITIVE LOGITS
     hand
    4.59
    hand
    3.28
    Hand
    2.88
     Hand
    2.59
     hands
    2.41
    手
    2.22
    HAND
    2.19
     HAND
    1.98
     mão
    1.91
    hands
    1.87
    Activations Density 0.014%

    No Known Activations