© 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. 67211
    Prev
    Next
    INDEX
    Explanations

    copyright years

    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
     Selección
    -1.49
     harap
    -1.34
    laria
    -1.29
     esponja
    -1.27
     Keramik
    -1.22
     Pueden
    -1.21
     potes
    -1.20
     Estación
    -1.20
     อาหาร
    -1.20
     života
    -1.20
    POSITIVE LOGITS
     ..
    1.38
     –
    1.34
    -
    1.16
           
    1.15
    ↵↵
    1.13
     &
    1.11
         
    1.09
    $
    1.08
     !!!
    1.08
     /
    1.08
    Activations Density 0.004%

    No Known Activations