© 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. 50511
    Prev
    Next
    INDEX
    Explanations

    either

    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
     kans
    -0.80
     third
    -0.72
    onz
    -0.71
    ținut
    -0.68
     bout
    -0.68
     Meskipun
    -0.68
     dout
    -0.67
     devils
    -0.66
     pal
    -0.66
     ल
    -0.66
    POSITIVE LOGITS
     Chim
    0.85
    YER
    0.76
    ㎍
    0.73
    しめ
    0.73
    つまみ
    0.71
    THC
    0.70
     edward
    0.68
    θρω
    0.68
    iven
    0.66
     FSA
    0.65
    Activations Density 0.088%

    No Known Activations