© 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. 47953
    Prev
    Next
    INDEX
    Explanations

    starts with hi

    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
    A
    0.50
    HELLO
    0.48
    τά
    0.46
    жер
    0.45
    <0x8F>
    0.45
     logarithm
    0.45
    Sincerely
    0.44
    ู
    0.44
     코로나
    0.43
    Tottenham
    0.43
    POSITIVE LOGITS
     guys
    0.63
     خیلی
    0.57
     druga
    0.54
     incompl
    0.54
     terk
    0.52
    いる
    0.52
     çık
    0.52
     imbib
    0.52
    ls
    0.51
     utilise
    0.50
    Activations Density 0.021%

    No Known Activations