© 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. 10-GEMMASCOPE-RES-131K
    7. 39254
    Prev
    Next
    INDEX
    Explanations

    repeated characters and numbers

    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
    ICIÓN
    -1.70
    彀
    -1.67
     creates
    -1.54
     makes
    -1.52
     their
    -1.52
    矢量
    -1.46
     says
    -1.45
    演示
    -1.45
    (￣
    -1.45
     seemed
    -1.43
    POSITIVE LOGITS
     stuks
    1.73
    TAINMENT
    1.73
    });
    1.63
     هذه
    1.63
     solches
    1.57
    ":
    1.48
     üblichen
    1.48
     tył
    1.46
     novembro
    1.46
     jego
    1.46
    Activations Density 0.001%

    No Known Activations