© 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. 33048
    Prev
    Next
    INDEX
    Explanations

    heterogeneity, pressure response, additional information, questions

    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
    Even
    -1.02
     even
    -0.99
     даже
    -0.92
     Even
    -0.88
    ඔ
    -0.81
    even
    -0.79
     nawet
    -0.78
     
    -0.77
    legate
    -0.75
    Extended
    -0.73
    POSITIVE LOGITS
     essentiellement
    0.88
     abbildung
    0.82
     dvě
    0.81
     descri
    0.80
    mfg
    0.79
     gedeelte
    0.77
    stickers
    0.76
    ⑳
    0.76
     ritratto
    0.75
     "{
    0.74
    Activations Density 0.003%

    No Known Activations