© 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-TRANSCODER-262K
    7. 35862
    Prev
    Next
    INDEX
    Explanations

    relationship ending divorce breakup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     sight
    0.41
    юра
    0.36
     transformed
    0.36
     Pisa
    0.36
    THROW
    0.36
    Transitions
    0.35
    
    0.35
    顗
    0.35
     ò
    0.35
     tra
    0.35
    POSITIVE LOGITS
     marido
    0.49
     suami
    0.47
     manžel
    0.45
     husband
    0.43
     супру
    0.43
     marriages
    0.40
    伉
    0.40
     esposo
    0.39
     marital
    0.39
     вскоре
    0.39
    Activations Density 0.005%

    No Known Activations