© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74401
    Prev
    Next
    INDEX
    Explanations

    june dates and names

    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
    .”
    -3.19
     水着
    -2.64
    ⫾
    -2.63
    
    -2.63
    ,’
    -2.56
    ⽩
    -2.50
    ﹶ
    -2.45
    ᭡
    -2.39
    
    -2.39
     bagaimana
    -2.39
    POSITIVE LOGITS
    '
    3.36
    (
    3.27
    1
    2.94
    –
    2.83
     {
    2.75
     '
    2.44
     "
    2.42
    釓
    2.36
    ."
    2.28
    r
    2.28
    Activations Density 0.004%

    No Known Activations