© 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. 38563
    Prev
    Next
    INDEX
    Explanations

    country or place 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
     mismos
    -0.86
    繳
    -0.84
     when
    -0.82
     that
    -0.82
     أثناء
    -0.81
    骶
    -0.81
    quantum
    -0.81
     during
    -0.81
    まります
    -0.80
     vänner
    -0.79
    POSITIVE LOGITS
    Captor
    1.05
    andaş
    0.94
    キャベツ
    0.93
     if
    0.89
     если
    0.88
     seraient
    0.88
     Joshi
    0.86
    encial
    0.85
     décès
    0.85
     завода
    0.85
    Activations Density 0.017%

    No Known Activations