© 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. 59990
    Prev
    Next
    INDEX
    Explanations

    describing flatness

    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
    ;++
    -0.77
    Rotated
    -0.73
    писки
    -0.71
    ˀ
    -0.71
    rapie
    -0.71
    onomics
    -0.70
    ῾
    -0.70
    ToLeft
    -0.70
    ()-
    -0.68
     Dixon
    -0.68
    POSITIVE LOGITS
     flat
    5.53
    flat
    4.78
    Flat
    4.22
     Flat
    4.09
     FLAT
    4.00
    FLAT
    3.73
    平
    3.59
     flatter
    3.42
     flats
    2.98
     flatten
    2.95
    Activations Density 0.075%

    No Known Activations