© 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. 22-GEMMASCOPE-RES-131K
    7. 12679
    Prev
    Next
    INDEX
    Explanations

    photographer or photography

    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_22/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
    or
    -3.28
    2
    -3.06
     was
    -3.05
    ?"
    -2.92
    \
    -2.77
     '
    -2.64
    1
    -2.61
    at
    -2.61
     /
    -2.45
     are
    -2.44
    POSITIVE LOGITS
    鈈
    2.67
    祼
    2.66
     帅气
    2.59
    тории
    2.55
    葙
    2.53
    轫
    2.52
     ſol
    2.50
    
    2.42
    敺
    2.42
    讠
    2.41
    Activations Density 0.013%

    No Known Activations