© 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. 10-GEMMASCOPE-RES-131K
    4. 330
    Prev
    Next
    INDEX
    Explanations

    odds ratios and statistical factors

    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_10/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
    ibile
    -1.25
    PRWEB
    -1.24
    pso
    -1.21
     synthesizer
    -1.20
     Agence
    -1.19
     عنها
    -1.19
    bahnhof
    -1.19
     विश्वसनीय
    -1.17
     noastre
    -1.17
     لكن
    -1.16
    POSITIVE LOGITS
     propio
    1.43
     on
    1.42
    是一種
    1.34
    2
    1.30
    ("
    1.29
     młody
    1.27
     neuen
    1.24
     modernen
    1.22
     hely
    1.22
     algun
    1.22
    Activations Density 0.054%

    No Known Activations