© 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. 10-GEMMASCOPE-RES-131K
    4. 37
    Prev
    Next
    INDEX
    Explanations

    winning excellence

    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
    猡
    -2.45
     '
    -2.42
     asesin
    -2.28
     expedited
    -2.17
    "",
    
    -2.16
    ="")
    -2.11
    ='')
    -2.09
     juzg
    -2.09
    逦
    -2.08
    全力
    -2.06
    POSITIVE LOGITS
    ねぇ
    2.48
    Without
    2.48
    During
    2.45
    Maybe
    2.41
    Usually
    2.38
    All
    2.33
    Though
    2.33
    Many
    2.31
    Before
    2.25
    Although
    2.25
    Activations Density 0.013%

    No Known Activations