© 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. 33727
    Prev
    Next
    INDEX
    Explanations

    theorems, lemmas, and propositions

    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
    robe
    -0.90
     抽象
    -0.86
    antwortung
    -0.85
    skie
    -0.78
    chè
    -0.78
    panes
    -0.78
    duo
    -0.77
     人生
    -0.76
    יבות
    -0.76
     %=
    -0.75
    POSITIVE LOGITS
     Proposition
    3.45
     Lemma
    3.30
    Proposition
    3.27
     Theorem
    3.08
    Lemma
    2.88
     proposition
    2.78
    Theorem
    2.73
     lemma
    2.50
     theorem
    2.42
     Corollary
    2.33
    Activations Density 0.041%

    No Known Activations