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. 1911
    Prev
    Next
    INDEX
    Explanations

    Key improvements and explanations

    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
    ওয়ার্ড
    0.39
     Leighton
    0.39
     ಇದೆ
    0.36
    èves
    0.36
    朢
    0.36
     diminutive
    0.36
     takeaway
    0.35
    <unused94>
    0.34
     υψη
    0.34
    rectomy
    0.34
    POSITIVE LOGITS
    BUG
    0.47
     Features
    0.47
     Added
    0.47
     updates
    0.46
    update
    0.46
     bug
    0.46
     Bug
    0.46
     added
    0.46
     prueba
    0.45
     업데이트
    0.43
    Activations Density 0.005%

    No Known Activations