© 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. 50197
    Prev
    Next
    INDEX
    Explanations

    cardinal directions and regions

    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
    komple
    -0.77
     membranes
    -0.73
     اصلاح
    -0.73
    jetzt
    -0.72
    ัญ
    -0.72
    nault
    -0.71
    stanbul
    -0.71
     suffisamment
    -0.71
     leggere
    -0.70
    碰到
    -0.70
    POSITIVE LOGITS
    omaterial
    0.82
    ਲ
    0.79
    ophora
    0.78
     фор
    0.76
    ouin
    0.76
     even
    0.72
    bmi
    0.70
     entities
    0.70
    race
    0.70
    Huff
    0.69
    Activations Density 0.073%

    No Known Activations