© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116027
    Prev
    Next
    INDEX
    Explanations

    places and names

    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
     okaz
    -0.78
     thaw
    -0.78
    viš
    -0.75
    pis
    -0.74
    licenses
    -0.73
    urta
    -0.73
    ガール
    -0.72
    }>{
    -0.71
    license
    -0.71
    algebras
    -0.71
    POSITIVE LOGITS
     Georgian
    0.91
     Huron
    0.80
     GED
    0.75
     PPA
    0.73
    lwz
    0.71
     Toshiba
    0.71
     Azerbai
    0.71
    Vedi
    0.71
     Bruce
    0.69
     Sarawak
    0.69
    Activations Density 0.025%

    No Known Activations