© 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. 81579
    Prev
    Next
    INDEX
    Explanations

    Supernatural characters and elements

    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
    غرافيا
    -0.77
    İK
    -0.77
    无双
    -0.73
    CIT
    -0.71
     cuesta
    -0.70
    onges
    -0.69
     Dudley
    -0.69
    Cactus
    -0.68
     Armored
    -0.68
     grazed
    -0.67
    POSITIVE LOGITS
     Winchester
    1.72
     Supernatural
    1.43
     Dean
    1.24
     Impala
    1.19
    Dean
    1.19
    Win
    1.05
     Вин
    1.05
     Sam
    1.05
    Sam
    1.04
     hunters
    1.03
    Activations Density 0.008%

    No Known Activations