© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116642
    Prev
    Next
    INDEX
    Explanations

    names and their following words

    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
     Zauber
    -0.94
    Esc
    -0.81
     fabrica
    -0.79
     اط
    -0.78
    ELE
    -0.77
    Ett
    -0.77
    Ṃ
    -0.76
    Fantastic
    -0.75
    ෆ
    -0.75
    Potential
    -0.75
    POSITIVE LOGITS
    ,,,,
    1.00
     состав
    0.75
     locals
    0.74
    ,,
    0.74
     appeal
    0.73
     жало
    0.72
    JUNE
    0.72
     Fitted
    0.72
     sanciones
    0.71
     marriage
    0.71
    Activations Density 0.140%

    No Known Activations