© 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. 22-GEMMASCOPE-RES-131K
    4. 93058
    Prev
    Next
    INDEX
    Explanations

    rectangles and bounding boxes

    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
    Perry
    -1.18
    Couleur
    -1.18
     壁纸
    -1.10
    dank
    -1.09
     INFORMACIÓN
    -1.07
    ılığı
    -1.04
    unno
    -1.02
    shein
    -1.02
     exprimer
    -1.01
    Niveau
    -1.00
    POSITIVE LOGITS
     bounds
    1.24
     CGRectMake
    1.17
     size
    1.14
     boundaries
    1.13
     sizes
    1.10
    잡
    1.08
    size
    1.03
     veckan
    1.03
     may
    1.02
     månader
    1.02
    Activations Density 0.025%

    No Known Activations