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. 53-GEMMASCOPE-2-RES-262K
    4. 1761
    Prev
    Next
    INDEX
    Explanations

    M

    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_53_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
     glLightfv
    0.38
    مط
    0.35
    SKAction
    0.33
     திருதியை
    0.33
    ද්ග
    0.32
     échanc
    0.32
    ッチン
    0.32
    <unused9>
    0.32
    <unused76>
    0.32
    addContainerGap
    0.32
    POSITIVE LOGITS
     M
    4.53
    M
    3.42
     М
    3.39
     الم
    2.81
     m
    2.64
    M
    2.52
     एम
    2.45
    М
    2.41
     ম
    2.33
     म
    2.27
    Activations Density 0.191%

    No Known Activations