© 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. 4383
    Prev
    Next
    INDEX
    Explanations

    parish names and place suffixes

    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
     Сем
    -0.73
     IN
    -0.72
    🦯
    -0.71
     in
    -0.69
     Stark
    -0.68
     issues
    -0.64
    Maw
    -0.64
    Ethyl
    -0.63
    Manufactured
    -0.63
     really
    -0.63
    POSITIVE LOGITS
    BOOL
    0.88
    AGH
    0.85
     뒤
    0.84
    看上去
    0.84
    スキ
    0.80
    ровал
    0.80
    kton
    0.80
    OUS
    0.80
    бору
    0.80
    boj
    0.79
    Activations Density 0.050%

    No Known Activations