© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32918
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     who
    -0.85
     experience
    -0.84
    =`
    -0.82
    olescence
    -0.82
    lippe
    -0.81
    othelioma
    -0.78
    rostis
    -0.77
    nological
    -0.75
     Drago
    -0.75
    ticed
    -0.74
    POSITIVE LOGITS
     نوج
    0.81
    Coyote
    0.80
     }\
    0.80
    BACA
    0.73
    avelmente
    0.71
    ето
    0.71
    варя
    0.70
    quartier
    0.70
    ISION
    0.69
     taille
    0.69
    Activations Density 0.000%

    No Known Activations