© 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. 34-GEMMASCOPE-RES-131K
    7. 1825
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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_34/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
    loro
    -0.81
    MUX
    -0.79
     kateg
    -0.79
    我就
    -0.78
     SP
    -0.77
    žití
    -0.75
    closures
    -0.74
    Cancellation
    -0.74
     mild
    -0.73
     desagrad
    -0.73
    POSITIVE LOGITS
    lič
    0.80
     rupiah
    0.76
     Cina
    0.76
     respira
    0.75
     său
    0.74
     manis
    0.74
    還能
    0.73
     Pediat
    0.73
    чните
    0.73
    exao
    0.71
    Activations Density 0.045%

    No Known Activations