© 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. 60435
    Prev
    Next
    INDEX
    Explanations

    Comparison of

    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
     Verpflich
    -0.90
    iteľ
    -0.90
     both
    -0.89
     campos
    -0.85
    namientos
    -0.81
    vės
    -0.80
     Vordergrund
    -0.79
     three
    -0.79
    øren
    -0.78
     rejuven
    -0.78
    POSITIVE LOGITS
     cuantas
    0.89
     conscientes
    0.87
     ERC
    0.83
    Rés
    0.82
     contratar
    0.82
     trad
    0.79
    Allgemeine
    0.79
     bia
    0.78
     baixar
    0.77
    uri
    0.76
    Activations Density 0.000%

    No Known Activations