© 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. 99124
    Prev
    Next
    INDEX
    Explanations

    All I'm doing is

    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
     niedersachsen
    -1.73
    
    -1.73
    翃
    -1.70
    裢
    -1.70
    鉏
    -1.69
     igra
    -1.68
     assiste
    -1.66
    粜
    -1.66
     akurat
    -1.66
     rafra
    -1.66
    POSITIVE LOGITS
     after
    2.25
     is
    2.05
    6
    2.03
    5
    1.95
    4
    1.94
     for
    1.82
     после
    1.80
    after
    1.77
     had
    1.76
    M
    1.74
    Activations Density 0.023%

    No Known Activations