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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12245
    Prev
    Next
    INDEX
    Explanations

    phrases with quotes or special characters

    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
    "
    0.53
    Example
    0.51
    问
    0.51
    *
    0.50
    faat
    0.46
    ");
    0.46
    example
    0.45
    nosti
    0.45
    Đ
    0.44
     أيضًا
    0.42
    POSITIVE LOGITS
     よく
    0.44
    ಿವ
    0.44
    ారం
    0.44
    igere
    0.43
    이스
    0.43
     vegetative
    0.43
     journe
    0.42
     フォー
    0.42
     ଗ
    0.42
     ବ
    0.42
    Activations Density 0.055%

    No Known Activations