© 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. 33797
    Prev
    Next
    INDEX
    Explanations

    Koihoma language

    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
    ashita
    -0.74
     China
    -0.74
     Patty
    -0.73
    RuntimeObject
    -0.73
     major
    -0.72
     Southeast
    -0.72
    нализ
    -0.72
    ˘
    -0.71
    ius
    -0.71
     promotion
    -0.71
    POSITIVE LOGITS
     Pollo
    0.98
    Moi
    0.93
    selle
    0.86
     ayuntamiento
    0.83
     coincid
    0.82
    Gek
    0.81
    soi
    0.81
     Moi
    0.79
     встроен
    0.78
     McInt
    0.77
    Activations Density 0.029%

    No Known Activations