© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20042
    Prev
    Next
    INDEX
    Explanations

    articles followed by 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_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
    因为它
    -1.63
     not
    -1.60
     लिए
    -1.52
     still
    -1.48
    n
    -1.47
    b
    -1.41
     mereka
    -1.40
     want
    -1.40
     chose
    -1.35
    但是在
    -1.34
    POSITIVE LOGITS
     incontri
    1.63
     sehingga
    1.56
     huesos
    1.54
    咴
    1.54
    addEvent
    1.53
    vikling
    1.48
    gemeester
    1.48
     puentes
    1.48
     orígenes
    1.45
    ౩
    1.44
    Activations Density 0.007%

    No Known Activations