© 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. 47915
    Prev
    Next
    INDEX
    Explanations

    Desperate Housewives or single moms

    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
    Anth
    -0.77
     Aprile
    -0.75
     Artik
    -0.73
    GTA
    -0.72
     torsdag
    -0.72
     Arqu
    -0.71
    Rhe
    -0.71
     Mallorca
    -0.71
    ங
    -0.71
    glDisable
    -0.70
    POSITIVE LOGITS
     Neigh
    0.83
     הפר
    0.81
     kế
    0.77
     Kylie
    0.75
    Kylie
    0.74
     Dodson
    0.73
     Lax
    0.72
    ACH
    0.71
    IMER
    0.70
     dataSet
    0.70
    Activations Density 0.018%

    No Known Activations