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. 11167
    Prev
    Next
    INDEX
    Explanations

    matrix multiplication

    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
    xym
    0.40
     racines
    0.38
    ptides
    0.37
    
    0.37
     scientifiques
    0.37
    otation
    0.37
     potrzeb
    0.36
    replacement
    0.35
    ()->
    0.35
    Scientific
    0.35
    POSITIVE LOGITS
     season
    0.42
    か
    0.40
     month
    0.39
     Krishna
    0.38
    শর
    0.38
     pert
    0.38
    的日子
    0.37
     месяца
    0.37
     सल्ला
    0.37
    компа
    0.36
    Activations Density 0.001%

    No Known Activations