© 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. 22-GEMMASCOPE-RES-131K
    7. 84506
    Prev
    Next
    INDEX
    Explanations

    sports and competition results

    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_22/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
     if
    -1.46
     or
    -1.37
     business
    -1.25
    effectiveness
    -1.23
     оно
    -1.16
    幼稚園
    -1.15
     it
    -1.13
    Когда
    -1.05
    lapsible
    -1.03
     بودند
    -1.03
    POSITIVE LOGITS
     fehler
    1.39
     tonight
    1.34
     atriz
    1.27
     procedimento
    1.27
     yesterday
    1.22
     scoring
    1.22
    styleable
    1.20
     segredo
    1.20
     Saturday
    1.20
     scores
    1.18
    Activations Density 0.013%

    No Known Activations