© 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. 184749
    Prev
    Next
    INDEX
    Explanations

    way until

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

    that * made

    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
     रजत
    0.47
    ﾃ
    0.45
     चिन्ह
    0.44
    不僅
    0.44
    profil
    0.43
     souligne
    0.43
    檔
    0.43
    million
    0.42
    還有
    0.42
    領域
    0.42
    POSITIVE LOGITS
     Gateway
    0.46
     长
    0.46
     Работа
    0.45
     വാക്ക
    0.44
    চ্ছা
    0.44
    TimeDict
    0.44
    ه‌های
    0.43
     副
    0.43
     muszą
    0.43
     gateways
    0.43
    Activations Density 0.000%

    No Known Activations