© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3007
    Prev
    Next
    INDEX
    Explanations

    words starting with th

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

    thong, throbbing, thawing, thundercats, thousand, thiourea

    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_53_width_65k_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
    jot
    0.43
    tional
    0.42
    tip
    0.38
    𝐝
    0.36
    tips
    0.36
    squeeze
    0.35
    sulf
    0.35
    的情
    0.35
    certificates
    0.34
    िटी
    0.34
    POSITIVE LOGITS
    嚨
    0.63
    咙
    0.59
     Th
    0.59
     థ
    0.58
    Th
    0.56
    الث
    0.56
     TH
    0.54
    waite
    0.54
     ಥ
    0.53
    لاث
    0.48
    Activations Density 0.130%

    No Known Activations