© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62059
    Prev
    Next
    INDEX
    Explanations

    describing context after a word

    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
    را
    0.51
    ៦
    0.48
    <0x9F>
    0.47
    aleza
    0.47
    ດີ
    0.47
    ೮
    0.47
    !')
    0.46
    ೯
    0.46
    ᱘
    0.45
    če
    0.45
    POSITIVE LOGITS
     inoculation
    0.42
    ReadAll
    0.41
     integração
    0.40
    涮
    0.40
    Pour
    0.39
    注射
    0.39
     nhìn
    0.38
     умолча
    0.38
     statute
    0.38
    工事
    0.38
    Activations Density 0.010%

    No Known Activations