© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126466
    Prev
    Next
    INDEX
    Explanations

    growth potential, provide access

    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
     да
    0.50
     ച
    0.45
    ра
    0.45
     па
    0.44
     у
    0.43
    દ
    0.43
     ко
    0.43
     Вас
    0.43
     Soll
    0.43
     Nó
    0.42
    POSITIVE LOGITS
     españ
    0.50
    美国
    0.45
     submarines
    0.44
    ⏳
    0.43
     statunitense
    0.43
    )([
    0.43
    rometry
    0.41
    HSI
    0.41
     سعودی
    0.41
     postseason
    0.41
    Activations Density 0.004%

    No Known Activations