© 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. 242131
    Prev
    Next
    INDEX
    Explanations

    issues by governing terms

    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
    டுகிறது
    0.48
    چ
    0.45
    asures
    0.44
    ম্‌
    0.44
    窃
    0.44
    습니다
    0.43
    ToArabic
    0.42
    ාල
    0.42
    럿
    0.41
     chegada
    0.41
    POSITIVE LOGITS
     حبي
    0.50
    ь
    0.47
    influenced
    0.46
    т
    0.46
    treating
    0.45
     কেন্দ্রের
    0.44
     settling
    0.43
    justice
    0.43
    当社
    0.43
    inspired
    0.42
    Activations Density 0.000%

    No Known Activations