© 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. 24090
    Prev
    Next
    INDEX
    Explanations

    represented

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

    Oahu vacation plans

    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
     คุณ
    0.53
     شما
    0.50
     تقریبا
    0.48
     ؟
    0.47
    дже
    0.44
     جنا
    0.44
     يمكنك
    0.44
     بدون
    0.43
     توسط
    0.43
     પ્રકાર
    0.43
    POSITIVE LOGITS
    岔
    0.53
    回归
    0.50
    引领
    0.48
    oulton
    0.46
     closer
    0.46
    ínio
    0.45
    မ့်
    0.45
    এ
    0.45
    வத
    0.45
    𝕌
    0.44
    Activations Density 0.000%

    No Known Activations