© 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. 115926
    Prev
    Next
    INDEX
    Explanations

    for sale

    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
     Hinsicht
    -0.83
     Leistung
    -0.82
     krę
    -0.80
     ante
    -0.79
     dzięki
    -0.78
     zwi
    -0.78
    Lambda
    -0.77
     Ante
    -0.77
    遡
    -0.77
     commencer
    -0.75
    POSITIVE LOGITS
     for
    3.58
     For
    2.42
     FOR
    2.34
     available
    2.22
    For
    2.22
    for
    2.09
     للبيع
    1.87
     sale
    1.81
    FOR
    1.80
     прода
    1.63
    Activations Density 0.051%

    No Known Activations