Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12337
    Prev
    Next
    INDEX
    Explanations

    passed away, gone

    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_16k_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
     হইতেই
    0.45
    簟
    0.42
    ཿ
    0.42
    atthakath
    0.42
    ٹی
    0.41
    स्मै
    0.38
    FileName
    0.38
    壹百
    0.37
    ᅪ
    0.37
    InputDir
    0.37
    POSITIVE LOGITS
     news
    0.44
     Covid
    0.41
     News
    0.40
     COVID
    0.40
     retirees
    0.37
     notizia
    0.36
     queridos
    0.36
    news
    0.35
    spo
    0.35
    </
    0.34
    Activations Density 0.039%

    No Known Activations