© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109075
    Prev
    Next
    INDEX
    Explanations

    foreign place names

    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
    imanapun
    -1.16
    škas
    -1.13
     wijze
    -1.02
    Another
    -0.96
     directly
    -0.96
    以色列
    -0.95
     vervol
    -0.95
    símbolo
    -0.94
    Pozdrawiam
    -0.94
     aiut
    -0.93
    POSITIVE LOGITS
    และ
    1.22
    それから
    1.16
    恐れ
    1.10
    それに
    1.10
    齟
    1.08
     chè
    1.05
    を
    1.05
    と
    1.04
     endorsements
    1.04
    があり
    1.04
    Activations Density 0.008%

    No Known Activations