© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 20031
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases

    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
    儂
    0.47
    check
    0.46
     депозит
    0.43
    county
    0.43
     జమ
    0.43
    ূল্যে
    0.42
     methodology
    0.41
    讓你
    0.40
     అధికారులు
    0.40
    Deputy
    0.39
    POSITIVE LOGITS
     existing
    0.41
    ಗಳು
    0.41
    uvian
    0.41
    인
    0.40
     fibr
    0.40
     Amerika
    0.39
    이었다
    0.39
    会自动
    0.39
     Omega
    0.39
     Eat
    0.39
    Activations Density 0.006%

    No Known Activations