© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50249
    Prev
    Next
    INDEX
    Explanations

    directional place names

    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
    ︲
    -0.93
     wahre
    -0.88
     وہ
    -0.83
     Produkte
    -0.82
    ParallelGroup
    -0.81
    various
    -0.81
    *=
    -0.80
    °.
    -0.78
     fria
    -0.77
    各种
    -0.77
    POSITIVE LOGITS
     part
    1.64
     часть
    1.20
     części
    1.18
    most
    1.11
     частью
    1.07
     بخشی
    1.06
     части
    1.05
    part
    1.00
     parts
    0.96
     portion
    0.96
    Activations Density 0.051%

    No Known Activations