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-16K
    4. 12685
    Prev
    Next
    INDEX
    Explanations

    tracking and following

    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
    >
    0.56
     restraint
    0.51
    $,
    0.49
    <td>
    0.47
    ebab
    0.47
    ம்
    0.45
    ристо
    0.44
    дри
    0.44
    렀
    0.43
     respite
    0.43
    POSITIVE LOGITS
    c
    0.59
    h
    0.59
    追踪
    0.58
    s
    0.58
     kịp
    0.57
     keting
    0.56
     Tracking
    0.55
     multinationals
    0.55
     updates
    0.54
    跟踪
    0.54
    Activations Density 0.162%

    No Known Activations