© 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. 3890
    Prev
    Next
    INDEX
    Explanations

    piezoelectricity, kidnapping, mathematical angles, Android UI/code

    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
    灕
    -3.06
    
    -2.84
    ⢓
    -2.81
    酲
    -2.59
     Ironically
    -2.58
    獁
    -2.56
    𖡼
    -2.52
    涷
    -2.44
    because
    -2.44
    to
    -2.36
    POSITIVE LOGITS
    ’
    2.91
     terrific
    2.89
     "
    2.81
     venden
    2.78
    饪
    2.75
     ancla
    2.69
     blatant
    2.61
    跄
    2.61
    掂
    2.61
     include
    2.59
    Activations Density 0.002%

    No Known Activations