© 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. 70219
    Prev
    Next
    INDEX
    Explanations

    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
     and
    -2.81
     trám
    -2.06
     okno
    -1.97
     disminución
    -1.96
     skvě
    -1.88
     nadru
    -1.83
    graffiti
    -1.81
     áng
    -1.80
     ráp
    -1.76
    meditation
    -1.76
    POSITIVE LOGITS
     more
    2.27
     There
    1.81
     It
    1.79
     they
    1.70
    на
    1.67
     If
    1.64
     only
    1.63
     Perhaps
    1.58
     Although
    1.58
     Einige
    1.55
    Activations Density 0.025%

    No Known Activations