© 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. 33540
    Prev
    Next
    INDEX
    Explanations

    Muslim 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
     命
    -0.79
    JD
    -0.79
     mounds
    -0.76
    ที่มา
    -0.76
     patrones
    -0.76
    ALLEL
    -0.75
     크
    -0.75
    }:=
    -0.74
    stanze
    -0.73
     Isk
    -0.73
    POSITIVE LOGITS
    жи
    0.78
    ╬
    0.73
    мети
    0.72
    Droid
    0.71
     Newtonsoft
    0.70
     フィギュア
    0.69
     MM
    0.69
    tivo
    0.68
    utum
    0.68
    below
    0.68
    Activations Density 0.017%

    No Known Activations