© 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. 80743
    Prev
    Next
    INDEX
    Explanations

    tied, tying, by, and past the

    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
     reconoce
    -0.96
    嗰
    -0.94
     jenes
    -0.89
    ズキ
    -0.82
     sw
    -0.79
    Източници
    -0.76
     minuman
    -0.76
     grossen
    -0.75
     Städte
    -0.75
    atological
    -0.75
    POSITIVE LOGITS
     the
    3.23
    the
    1.41
    ofthe
    1.35
    rethe
    1.21
    ethe
    1.21
    ザ
    1.17
    OfThe
    1.11
     THE
    1.10
     thé
    1.08
    nthe
    1.05
    Activations Density 0.157%

    No Known Activations