© 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. 34-GEMMASCOPE-RES-131K
    7. 107720
    Prev
    Next
    INDEX
    Explanations

    George Thomas

    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
     CheckBox
    -0.77
     qualification
    -0.77
     clean
    -0.72
    qualification
    -0.70
     shortage
    -0.69
    不用
    -0.69
     campo
    -0.69
     early
    -0.68
     Fär
    -0.68
     moderno
    -0.67
    POSITIVE LOGITS
     Barbarian
    0.83
    llar
    0.79
     Caes
    0.74
    Quota
    0.74
    asive
    0.73
    ANCO
    0.72
    ﻟ
    0.72
    IOUtils
    0.71
    })();
    0.71
    reas
    0.71
    Activations Density 0.012%

    No Known Activations