© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101063
    Prev
    Next
    INDEX
    Explanations

    before the big bang

    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
     बेटी
    0.48
    થે
    0.48
     unusually
    0.48
    બે
    0.46
    ôtels
    0.45
     ஆகியவை
    0.45
     Ն
    0.45
    <unused979>
    0.45
    পাত্র
    0.44
    erçe
    0.44
    POSITIVE LOGITS
     injustices
    0.46
    getFullYear
    0.42
    supabase
    0.42
    t
    0.41
    ?"
    0.41
     untold
    0.39
    viewDidLoad
    0.39
     écoul
    0.39
     subjug
    0.39
    !"
    0.38
    Activations Density 0.010%

    No Known Activations