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. 14734
    Prev
    Next
    INDEX
    Explanations

    qualifier for specific terms

    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
     जेटली
    0.44
    庴
    0.43
    Chk
    0.41
     बजकर
    0.40
    affee
    0.39
    CTL
    0.39
     unintentional
    0.39
    قيقة
    0.39
     quinine
    0.38
     больш
    0.38
    POSITIVE LOGITS
     Api
    0.46
    それぞれ
    0.42
     Universidade
    0.40
     क्रमश
    0.39
    𝒈
    0.39
    南北
    0.38
     Dal
    0.38
     constituent
    0.38
     داخ
    0.37
    leder
    0.37
    Activations Density 1.801%

    No Known Activations