© 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. 76560
    Prev
    Next
    INDEX
    Explanations

    common word followed by another common word

    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
    ไม่
    0.47
     ۔
    0.47
    нести
    0.46
    يا
    0.45
    ิร์
    0.45
     zobac
    0.45
     воспользоваться
    0.45
     această
    0.44
    ั่ว
    0.44
     içeri
    0.44
    POSITIVE LOGITS
     imo
    0.41
    ufthansa
    0.39
    អេឡិចត្រូនិច
    0.39
    <unused664>
    0.39
    <unused681>
    0.39
    <unused1169>
    0.39
    triangleright
    0.38
     prodigious
    0.37
    roud
    0.37
    ())
    0.36
    Activations Density 0.007%

    No Known Activations