© 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. 98493
    Prev
    Next
    INDEX
    Explanations

    Oct dates

    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
     such
    -0.85
    мять
    -0.77
     ナイロン
    -0.77
     Northeastern
    -0.77
    deu
    -0.76
     tzw
    -0.76
     so
    -0.75
     a
    -0.73
    rp
    -0.73
    namics
    -0.73
    POSITIVE LOGITS
    grimas
    0.84
     mib
    0.81
     fingertips
    0.81
    izophrenia
    0.79
     οποία
    0.79
     sherds
    0.79
     tubuh
    0.79
    nexo
    0.78
     Pizarro
    0.78
     治療
    0.78
    Activations Density 0.007%

    No Known Activations