© 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. 99822
    Prev
    Next
    INDEX
    Explanations

    license text or code structure

    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
     展
    -0.76
     figlia
    -0.71
     Warburton
    -0.71
    ꯒ
    -0.71
    すぐ
    -0.69
    Toby
    -0.66
     István
    -0.66
    atcher
    -0.66
    FactoryBean
    -0.65
    原创
    -0.64
    POSITIVE LOGITS
    訂
    0.70
     razy
    0.66
    述
    0.65
    を利用
    0.64
     λά
    0.64
     Midwest
    0.64
    atyana
    0.63
    um
    0.63
    Authorization
    0.63
    imb
    0.63
    Activations Density 0.040%

    No Known Activations