© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58873
    Prev
    Next
    INDEX
    Explanations

    automotive insurance / portable device

    np_acts-logits-general · gemini-2.5-flash-lite

    connects or follows "it"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     மாநக
    0.49
    皞
    0.43
    蒨
    0.43
    穵
    0.42
    Spray
    0.41
    שוט
    0.41
    潵
    0.40
    陖
    0.40
    ικο
    0.40
    伈
    0.40
    POSITIVE LOGITS
     meningkat
    0.50
     in
    0.48
     hutan
    0.48
     memilih
    0.48
     iklan
    0.47
     prediksi
    0.47
     menget
    0.47
     nomor
    0.47
     assets
    0.46
     keinginan
    0.46
    Activations Density 0.000%

    No Known Activations