© 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. 55935
    Prev
    Next
    INDEX
    Explanations

    Southwestern regions and entities

    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
    "%(
    -0.69
    🧛
    -0.68
    *****/
    -0.68
    waypoint
    -0.67
    lyte
    -0.67
     suç
    -0.67
     よう
    -0.67
     nyelven
    -0.67
    tack
    -0.66
    ۩
    -0.66
    POSITIVE LOGITS
     SW
    1.05
    SW
    0.95
     sw
    0.82
    Sw
    0.82
    sw
    0.82
     SWR
    0.81
     arşivlendi
    0.80
     Sw
    0.76
    今回
    0.76
    minente
    0.76
    Activations Density 0.042%

    No Known Activations