© 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. 107774
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     Putih
    -0.88
     pred
    -0.85
    麟
    -0.81
     slam
    -0.79
     vag
    -0.79
    ร
    -0.79
     tribunal
    -0.77
     inspections
    -0.76
    кож
    -0.76
     Surgeons
    -0.75
    POSITIVE LOGITS
    iN
    0.91
     calentamiento
    0.82
     IW
    0.81
    ţin
    0.80
     pliable
    0.77
    endi
    0.77
    ंदी
    0.77
    专业的
    0.76
    报警
    0.74
     تشکر
    0.74
    Activations Density 1.260%

    No Known Activations