© 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. 98750
    Prev
    Next
    INDEX
    Explanations

    Japanese names and titles

    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
     हु
    -0.81
    Nhan
    -0.80
     is
    -0.78
     कोण
    -0.76
     außen
    -0.76
    압
    -0.75
     inds
    -0.73
    bdf
    -0.73
    キス
    -0.72
    Dawg
    -0.72
    POSITIVE LOGITS
    cchi
    1.05
     beslut
    1.05
     största
    1.00
    ǿ
    0.97
     aktiviteter
    0.96
    thanx
    0.93
    hada
    0.93
     dibujar
    0.93
    wickshire
    0.93
    annica
    0.91
    Activations Density 0.012%

    No Known Activations