© 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. 46271
    Prev
    Next
    INDEX
    Explanations

    Arabic conjunctions and English question words

    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
     thoracique
    0.60
     정의역
    0.60
     desigualdad
    0.58
     musculaire
    0.56
    瓤
    0.56
     incluidas
    0.55
    าร์
    0.55
    ко
    0.55
     diem
    0.55
    дие
    0.55
    POSITIVE LOGITS
    ON
    0.77
    </strong>
    0.73
    ä
    0.72
    ności
    0.70
    č
    0.66
    á
    0.64
    </h1>
    0.64
    {
    0.64
    NA
    0.64
    oc
    0.63
    Activations Density 0.001%

    No Known Activations