© 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. 76434
    Prev
    Next
    INDEX
    Explanations

    February 29 or leap day

    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
    lini
    -0.79
    疎
    -0.76
     giggled
    -0.74
     Borja
    -0.73
    ocry
    -0.73
    Prevent
    -0.73
     Apertura
    -0.72
     weken
    -0.72
    Ort
    -0.71
    РЭ
    -0.71
    POSITIVE LOGITS
     leap
    2.58
     Leap
    2.36
    Leap
    2.11
    leap
    1.90
     leaping
    1.50
     leaps
    1.45
     leaped
    1.40
     leapt
    1.30
    闰
    1.27
    閏
    1.14
    Activations Density 0.027%

    No Known Activations