© 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. 22-GEMMASCOPE-RES-131K
    7. 38635
    Prev
    Next
    INDEX
    Explanations

    proper nouns and quotes

    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
    %;
    -1.06
     mitos
    -1.05
    なんだけど
    -1.01
     kapal
    -1.00
     Traité
    -0.99
     trenger
    -0.99
    なんですが
    -0.98
    𝐆
    -0.95
     черный
    -0.95
    %;">
    -0.93
    POSITIVE LOGITS
    นาด
    1.18
    𝐳
    1.05
     ответить
    1.02
    1
    1.00
    8
    0.99
     inşa
    0.97
    即将
    0.96
     tambahan
    0.96
    全都
    0.96
    これらの
    0.95
    Activations Density 0.006%

    No Known Activations