© 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. 55722
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    〓
    -0.81
     Yadav
    -0.79
    Ḳ
    -0.76
     ayuda
    -0.76
    limits
    -0.75
    arxiv
    -0.72
     PLANS
    -0.70
     huit
    -0.69
    Ḥ
    -0.68
     наших
    -0.68
    POSITIVE LOGITS
    5
    1.22
     fifty
    0.86
     ۲۵
    0.85
     fifteenth
    0.84
    ).(
    0.81
    Ode
    0.79
     WN
    0.78
    rieron
    0.78
     نیم
    0.75
    četně
    0.75
    Activations Density 0.074%

    No Known Activations