© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 84638
    Prev
    Next
    INDEX
    Explanations

    Korean sentence endings

    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_40_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
     either
    0.42
    pet
    0.41
    use
    0.37
    either
    0.37
    Diag
    0.36
    dat
    0.35
    可以将
    0.35
    <span>
    0.34
     bark
    0.34
    pip
    0.34
    POSITIVE LOGITS
    了起来
    0.51
    了出来
    0.49
     ፣
    0.47
     등의
    0.46
    icuous
    0.45
     것이다
    0.45
    了下来
    0.44
     모습
    0.44
    成为了
    0.44
    くらいの
    0.44
    Activations Density 0.012%

    No Known Activations