© 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. 60498
    Prev
    Next
    INDEX
    Explanations

    contextual help

    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
    ก็
    -0.81
     before
    -0.79
    Ⓖ
    -0.76
     ವ
    -0.75
    мно
    -0.75
     قبل
    -0.74
     temperatur
    -0.74
    uego
    -0.73
     так
    -0.73
     Arquivado
    -0.72
    POSITIVE LOGITS
     help
    1.29
    help
    1.03
     Help
    1.02
     HELP
    0.86
     helpt
    0.85
     envision
    0.85
    fdb
    0.84
     Hilfe
    0.84
    helps
    0.83
     prompting
    0.83
    Activations Density 0.000%

    No Known Activations