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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 39962
    Prev
    Next
    INDEX
    Explanations

    covered from insurance

    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_65k_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
    ì
    0.48
    s
    0.46
    нг
    0.46
    ë
    0.44
    ху
    0.41
    ljen
    0.41
    تون
    0.40
    à
    0.40
    ی
    0.39
    autore
    0.38
    POSITIVE LOGITS
     becomes
    0.48
     is
    0.43
     xaxis
    0.42
     Without
    0.41
     daripada
    0.40
     Coalition
    0.39
    ረጥ
    0.39
     makes
    0.39
     위해서는
    0.38
     ใน
    0.38
    Activations Density 0.010%

    No Known Activations