© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120087
    Prev
    Next
    INDEX
    Explanations

    multi-lingual words and phrases

    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_16_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
    ר
    1.19
    ي
    0.84
    ر
    0.84
    ه
    0.83
    g
    0.81
    e
    0.80
    K
    0.77
    י
    0.70
    t
    0.68
    א
    0.68
    POSITIVE LOGITS
     బ్యాం
    0.80
     généralement
    0.68
     عدد
    0.68
     πίνακα
    0.67
    一個
    0.66
     ενός
    0.66
     промышлен
    0.65
    ूबी
    0.64
    <unused2213>
    0.64
     zásobníku
    0.64
    Activations Density 0.001%

    No Known Activations