Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8258
    Prev
    Next
    INDEX
    Explanations

    pen links

    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
     Gemeinsame
    -1.01
     GREY
    -0.91
    ⤞
    -0.90
    сного
    -0.87
    letti
    -0.84
    UNIDENTIFIED
    -0.83
     engels
    -0.83
     tyd
    -0.82
    pence
    -0.80
    ặt
    -0.79
    POSITIVE LOGITS
     conducted
    0.77
     wretched
    0.72
     bună
    0.71
     espesor
    0.71
    合う
    0.71
     experi
    0.71
    brica
    0.71
    どこに
    0.68
     ligera
    0.68
    foque
    0.67
    Activations Density 0.002%

    No Known Activations