© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117794
    Prev
    Next
    INDEX
    Explanations

    proper nouns and identifiers

    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
    щему
    -0.82
    Quic
    -0.79
     줄
    -0.79
    ρύ
    -0.78
    ベツ
    -0.78
    ctid
    -0.76
    ข้าว
    -0.76
     UML
    -0.76
    demie
    -0.75
    barang
    -0.75
    POSITIVE LOGITS
    kje
    0.84
     sehe
    0.80
    għ
    0.77
     紫色
    0.75
     trước
    0.75
    himself
    0.75
     ТЕ
    0.74
     predictive
    0.74
    vägen
    0.73
    textTheme
    0.72
    Activations Density 0.002%

    No Known Activations