© 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. 19256
    Prev
    Next
    INDEX
    Explanations

    sentiment words

    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
    ("")]
    -1.66
     At
    -1.62
    asanjo
    -1.60
     员
    -1.50
    fgaben
    -1.50
    紲
    -1.48
     come
    -1.47
    jarah
    -1.46
    +}\
    -1.45
     благодаря
    -1.44
    POSITIVE LOGITS
    or
    1.63
    或者
    1.57
     about
    1.57
     zacht
    1.55
     hunne
    1.55
     avto
    1.48
    橚
    1.47
     parachoque
    1.45
    ☹
    1.44
    [
    1.43
    Activations Density 0.015%

    No Known Activations