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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2305
    Prev
    Next
    INDEX
    Explanations

    italicized or code text followed by specific words

    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_262k_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
    Bạn
    0.22
    Nếu
    0.20
     Είναι
    0.20
    Không
    0.18
    馕
    0.18
    └
    0.18
     একটা
    0.18
     arrivé
    0.18
     Ebay
    0.18
    ◾
    0.18
    POSITIVE LOGITS
    kont
    0.21
    otro
    0.19
    elan
    0.19
    alten
    0.19
    트
    0.19
    онов
    0.19
    antes
    0.18
    Kont
    0.18
    on
    0.18
    ipso
    0.18
    Activations Density 0.782%

    No Known Activations