© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29578
    Prev
    Next
    INDEX
    Explanations

    site-specific data

    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
    ,{
    0.44
     gră
    0.40
    アク
    0.37
     κάθε
    0.36
     siapa
    0.36
     birkaç
    0.36
     cupcakes
    0.35
     mindig
    0.35
    潛
    0.35
     cik
    0.35
    POSITIVE LOGITS
    iyu
    0.42
    UIntValue
    0.41
     competency
    0.38
    źnie
    0.38
    èle
    0.38
     Idani
    0.37
    领
    0.37
    ppage
    0.36
    oons
    0.36
    maları
    0.36
    Activations Density 0.000%

    No Known Activations