© 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. 13853
    Prev
    Next
    INDEX
    Explanations

    historical dates

    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
    8
    -1.63
    7
    -1.53
     they
    -1.53
    4
    -1.45
    6
    -1.44
    5
    -1.43
    鯷
    -1.42
    Suerte
    -1.41
    "):
    -1.37
    four
    -1.36
    POSITIVE LOGITS
    '
    1.45
    
    1.28
     głównie
    1.26
    ков
    1.23
     następnie
    1.22
     červená
    1.21
     developing
    1.20
     Послед
    1.20
    doğan
    1.16
     černé
    1.15
    Activations Density 0.046%

    No Known Activations