© 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. 75803
    Prev
    Next
    INDEX
    Explanations

    United States

    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
     Yerevan
    -0.86
    ynes
    -0.84
    ڀ
    -0.81
    ꒦
    -0.73
    Armenia
    -0.72
     screws
    -0.71
    mediated
    -0.70
     Armenian
    -0.69
     Hoffnung
    -0.69
     Armenia
    -0.68
    POSITIVE LOGITS
    Ẵ
    0.86
     chines
    0.82
    iaire
    0.78
     evolu
    0.78
    льника
    0.78
     koordin
    0.77
     inverno
    0.77
     terce
    0.76
    Vitals
    0.76
     initialState
    0.75
    Activations Density 0.006%

    No Known Activations