© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113325
    Prev
    Next
    INDEX
    Explanations

    Debit Card, Kampfer, July, Q:

    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
     tjen
    -1.89
    '\\
    -1.75
    
    -1.73
    elts
    -1.73
     samarbe
    -1.70
     huelga
    -1.69
    ༵
    -1.63
    躂
    -1.63
     støtte
    -1.63
     musi
    -1.63
    POSITIVE LOGITS
     saying
    1.67
    0
    1.58
    These
    1.55
     predecess
    1.53
     do
    1.52
    7
    1.51
    8
    1.49
     about
    1.43
    While
    1.42
     see
    1.41
    Activations Density 0.006%

    No Known Activations