© 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. 6905
    Prev
    Next
    INDEX
    Explanations

    contrary to belief or expectation

    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
     لقد
    -0.86
    sort
    -0.85
     Dose
    -0.85
     także
    -0.80
    Kro
    -0.79
    *}$
    -0.79
    Kategorie
    -0.79
     laiton
    -0.79
    SuspendLayout
    -0.78
    тина
    -0.78
    POSITIVE LOGITS
     to
    1.77
     popular
    1.63
    popular
    1.30
     Contrary
    1.27
     belief
    1.23
    Contrary
    1.11
     распростран
    1.03
     contrary
    1.02
     perhaps
    0.99
     Popular
    0.99
    Activations Density 0.009%

    No Known Activations