© 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. 202045
    Prev
    Next
    INDEX
    Explanations

    sports events and finance

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

    process seamless, bodies tell, virtual box

    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
    旂
    0.45
    European
    0.43
    갈
    0.43
    וג
    0.42
    ומ
    0.42
    Ou
    0.42
    เซ
    0.42
    玻
    0.42
    ום
    0.41
    传统
    0.41
    POSITIVE LOGITS
     koja
    0.52
     sz
    0.50
     ngunit
    0.50
     willfully
    0.49
     pylori
    0.48
     która
    0.47
     mutta
    0.47
     Demir
    0.46
     បាន
    0.46
     ktorá
    0.45
    Activations Density 0.001%

    No Known Activations