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. 1826
    Prev
    Next
    INDEX
    Explanations

    Cyprus

    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
    竺
    0.44
    িউ
    0.44
    gown
    0.40
     अर्जेंटीना
    0.38
    Ꮽ
    0.38
    Seattle
    0.38
     mexico
    0.37
    태
    0.37
    ActionMode
    0.37
     remarque
    0.37
    POSITIVE LOGITS
     Cyprus
    1.88
     Cyp
    1.72
     cyst
    1.13
     Cypress
    1.05
     Larn
    1.05
     Cyst
    1.02
     CYP
    0.96
     cypress
    0.93
    Cy
    0.92
     قبر
    0.89
    Activations Density 0.005%

    No Known Activations