© 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. 72421
    Prev
    Next
    INDEX
    Explanations

    actions following to

    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
     on
    -1.84
     of
    -1.69
    m
    -1.61
     these
    -1.55
    D
    -1.52
        
    -1.43
    d
    -1.41
    t
    -1.41
     by
    -1.40
    n
    -1.38
    POSITIVE LOGITS
    zás
    1.89
    cún
    1.83
     Scritto
    1.79
    vollen
    1.73
    fought
    1.73
    葙
    1.71
    ⟣
    1.70
    橚
    1.66
     nové
    1.64
    ⎔
    1.63
    Activations Density 0.076%

    No Known Activations