© 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. 245053
    Prev
    Next
    INDEX
    Explanations

    specific items and actions

    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
    ↵
    0.42
     অন্যত্র
    0.38
    উল্লেখ্য
    0.37
     episode
    0.37
    newInstance
    0.36
    Framebuffer
    0.36
    “
    0.35
     aftermarket
    0.34
     illustrative
    0.34
    きっかけ
    0.34
    POSITIVE LOGITS
     wszystkie
    0.55
     અને
    0.49
     फक्त
    0.49
    جميع
    0.49
     மட்டுமே
    0.49
     ۽
    0.48
     आणि
    0.47
    ،
    0.47
     wretched
    0.46
     lelaki
    0.46
    Activations Density 0.002%

    No Known Activations