© 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. 22-GEMMASCOPE-RES-131K
    7. 104680
    Prev
    Next
    INDEX
    Explanations

    nation, Black, course, Zynga

    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_22/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
     compagnon
    -0.91
     whome
    -0.91
    :^(
    -0.90
    Gson
    -0.87
    Chỉ
    -0.83
     Judiciary
    -0.82
     espirituales
    -0.81
    ɵɵ
    -0.80
     különböz
    -0.79
    Укра
    -0.78
    POSITIVE LOGITS
     naturally
    1.55
     related
    1.44
    related
    1.37
    Naturally
    1.30
    naturally
    1.27
     Related
    1.17
     RELATED
    1.14
     naturalmente
    1.14
     Naturally
    1.09
     obvious
    1.09
    Activations Density 0.076%

    No Known Activations