© 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. 47951
    Prev
    Next
    INDEX
    Explanations

    outcome, state, or category nouns

    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
    直至
    -1.27
     lieu
    -1.16
     gmin
    -1.05
    来ました
    -1.02
     Flasche
    -0.95
    蚜
    -0.95
     minha
    -0.93
    ことから
    -0.92
     où
    -0.92
     ventaja
    -0.91
    POSITIVE LOGITS
    iniest
    1.20
     pengar
    1.18
    。
    1.16
    Depending
    1.08
     startX
    1.07
    Vezi
    1.05
    Leírás
    1.05
    maktadır
    1.02
     in
    1.02
     doká
    1.02
    Activations Density 0.018%

    No Known Activations