© 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. 49509
    Prev
    Next
    INDEX
    Explanations

    silver, bronze, medals

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

    chronic inflammation or crisis

    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
     ×
    0.47
    Live
    0.46
    *
    0.44
    track
    0.43
    ックス
    0.43
    <0xAD>
    0.42
     live
    0.42
     multiplied
    0.42
    careers
    0.41
    J
    0.41
    POSITIVE LOGITS
     ragged
    0.52
     বানিয়ে
    0.51
     প্রভৃতির
    0.51
    ikat
    0.49
    沬
    0.49
     आदी
    0.48
     মেরামত
    0.47
    பிலோ
    0.47
     टिका
    0.47
    upart
    0.46
    Activations Density 0.000%

    No Known Activations