© 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. 34-GEMMASCOPE-RES-131K
    7. 108825
    Prev
    Next
    INDEX
    Explanations

    wrap / wrapper

    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
     Nachhal
    -0.77
     cracking
    -0.76
     lò
    -0.73
    ˎ
    -0.73
    こち
    -0.70
     stood
    -0.69
     ")[
    -0.69
     sabes
    -0.69
    prometheus
    -0.68
     rapidly
    -0.68
    POSITIVE LOGITS
     unwra
    0.94
     confines
    0.78
    好吧
    0.78
     Wrapped
    0.77
    kommen
    0.77
    ofollow
    0.75
     Wra
    0.73
    gente
    0.73
    duino
    0.73
     Mots
    0.73
    Activations Density 0.009%

    No Known Activations