© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40088
    Prev
    Next
    INDEX
    Explanations

    multiple meanings and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    スタイル
    0.41
    承认
    0.37
    <0xBA>
    0.37
     языка
    0.36
     стиля
    0.36
    style
    0.36
     যন্ত্র
    0.36
     stylu
    0.36
     quanto
    0.36
    QSizePolicy
    0.36
    POSITIVE LOGITS
     ambiguities
    0.53
     ambiguous
    0.50
     disamb
    0.49
    曖
    0.49
     ambiguity
    0.48
     могли
    0.45
     surn
    0.45
     ambigu
    0.45
     несколь
    0.45
    disamb
    0.45
    Activations Density 0.138%

    No Known Activations