© 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. 113660
    Prev
    Next
    INDEX
    Explanations

    national railways

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

    translation skills; legendary recognition

    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
     prisms
    0.45
    ސ
    0.45
    getReference
    0.43
     autoimmunity
    0.42
    ্দ্র
    0.42
     polymeric
    0.42
     setSelected
    0.42
     positioned
    0.41
     polymers
    0.41
    τ
    0.41
    POSITIVE LOGITS
     नतीजा
    0.49
    S
    0.49
    yó
    0.48
     ผล
    0.47
     करावे
    0.47
     นาที
    0.46
     nghe
    0.45
     本当
    0.44
     koska
    0.44
     केल्यानंतर
    0.44
    Activations Density 0.000%

    No Known Activations