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. 40-GEMMASCOPE-2-RES-262K
    4. 18646
    Prev
    Next
    INDEX
    Explanations

    reckoning, reckless, reckoner

    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_40_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
    pyrim
    0.39
    ަން
    0.39
    leşik
    0.38
    цами
    0.38
     ارت
    0.38
    usch
    0.38
    byId
    0.37
    簧
    0.37
     claramente
    0.37
     setEmail
    0.37
    POSITIVE LOGITS
     rek
    0.65
    reck
    0.57
     Rek
    0.56
    Rek
    0.56
     Reck
    0.56
     reckon
    0.55
     Recurs
    0.55
     reckons
    0.54
     Rack
    0.52
     reckoning
    0.52
    Activations Density 0.006%

    No Known Activations