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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12019
    Prev
    Next
    INDEX
    Explanations

    questions about context

    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
    ५
    0.45
    룔
    0.45
    หมือน
    0.43
    ૨
    0.42
    ொண்டு
    0.42
    <0x8A>
    0.41
    ૢ
    0.40
    ÍN
    0.39
    ᱙
    0.39
    ७
    0.38
    POSITIVE LOGITS
     Why
    0.44
     That
    0.42
     But
    0.41
     why
    0.39
     How
    0.39
     If
    0.39
     Apparently
    0.38
     When
    0.38
     So
    0.37
     There
    0.37
    Activations Density 0.040%

    No Known Activations