© 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. 10-GEMMASCOPE-RES-131K
    7. 101638
    Prev
    Next
    INDEX
    Explanations

    negative propositions and indications

    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_10/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
    anything
    -1.56
    erver
    -1.51
    those
    -1.51
    perhaps
    -1.46
     penser
    -1.43
     marquées
    -1.38
    憷
    -1.38
    probably
    -1.38
    ed
    -1.37
    を引
    -1.37
    POSITIVE LOGITS
     only
    2.00
     ensures
    1.73
     allows
    1.71
     provides
    1.66
     enables
    1.64
     reduces
    1.64
     ensuring
    1.63
     with
    1.59
     just
    1.55
     helps
    1.53
    Activations Density 0.002%

    No Known Activations