© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200283
    Prev
    Next
    INDEX
    Explanations

    foreign language conjunctions

    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
     h
    0.42
    ského
    0.42
     crad
    0.42
     посредством
    0.41
    databind
    0.40
     epid
    0.39
     loài
    0.39
     CTE
    0.39
     PRE
    0.38
     runde
    0.38
    POSITIVE LOGITS
     પરંતુ
    0.49
    কাত
    0.45
     கூட்டணி
    0.44
    繽
    0.44
     ngunit
    0.44
     কিন্তু
    0.43
    rawValue
    0.42
    م
    0.42
    ใต้
    0.42
     하지만
    0.41
    Activations Density 0.002%

    No Known Activations