© 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. 103208
    Prev
    Next
    INDEX
    Explanations

    specific location context

    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
     Nasional
    -0.89
    íng
    -0.85
    amate
    -0.81
     Producción
    -0.79
     pune
    -0.78
    estre
    -0.78
    chak
    -0.76
    /'.$
    -0.75
     UserManager
    -0.75
    ライプ
    -0.73
    POSITIVE LOGITS
     lugar
    0.84
    コンビニ
    0.82
    Fart
    0.79
    Consul
    0.78
    穹
    0.76
     PASS
    0.75
    Maw
    0.74
    elementary
    0.73
    Alc
    0.73
    Interpre
    0.72
    Activations Density 0.001%

    No Known Activations