© 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-65K
    7. 47464
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by state or comparison

    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
     기대
    0.45
    他們的
    0.45
     зависит
    0.44
     их
    0.44
     符合
    0.44
    อื่น
    0.41
     attentes
    0.41
    ት
    0.41
    ផ្សេង
    0.40
     Drei
    0.40
    POSITIVE LOGITS
    Lorsque
    0.45
     próprio
    0.43
    اگر
    0.43
    おそらく
    0.43
     जेव्हा
    0.39
    或許
    0.39
    С
    0.39
    quando
    0.38
     lorsque
    0.37
    Jeśli
    0.37
    Activations Density 0.028%

    No Known Activations