© 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. 83202
    Prev
    Next
    INDEX
    Explanations

    specific names and concepts

    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
    __/
    -0.70
     LUT
    -0.69
     horoscope
    -0.65
    vdash
    -0.65
    Lob
    -0.65
     obscure
    -0.65
    weebly
    -0.65
    쓴
    -0.63
    Sql
    -0.63
    substring
    -0.63
    POSITIVE LOGITS
    ำ
    0.73
     nélkül
    0.72
     thirty
    0.71
     住宅
    0.68
     Brilliant
    0.67
    ICOL
    0.67
    痢
    0.65
     Чем
    0.65
     م
    0.64
    modules
    0.64
    Activations Density 0.541%

    No Known Activations