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. 9190
    Prev
    Next
    INDEX
    Explanations

    code elements and operations

    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
     wielu
    0.50
    ق
    0.42
     bazı
    0.42
    境内
    0.40
     kilku
    0.40
     பல
    0.39
    Innen
    0.39
     często
    0.38
     داخل
    0.38
    หลาย
    0.38
    POSITIVE LOGITS
     dioxide
    0.42
     indiquant
    0.42
     stateMutability
    0.40
    および
    0.39
    ➝
    0.39
     सरपंच
    0.39
     annotation
    0.38
    梔
    0.38
     glycine
    0.37
    鏨
    0.37
    Activations Density 0.024%

    No Known Activations